From diffserv-interest-admin@ietf.org Fri Sep 7 14:23:01 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id OAA22915 for ; Fri, 7 Sep 2001 14:23:01 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id OAA21821; Fri, 7 Sep 2001 14:22:38 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id OAA21790 for ; Fri, 7 Sep 2001 14:22:37 -0400 (EDT) Received: from anomaly.mit.edu (h0050dac9ca55.ne.mediaone.net [66.31.90.118]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id OAA22895 for ; Fri, 7 Sep 2001 14:21:09 -0400 (EDT) Received: from localhost (localhost [[UNIX: localhost]]) by anomaly.mit.edu (8.11.0/8.11.0) id f87IMWR11868 for diffserv-interest@ietf.org; Fri, 7 Sep 2001 14:22:32 -0400 Content-Type: text/plain; charset="iso-8859-1" From: Jon Salz To: diffserv-interest@ietf.org Date: Fri, 7 Sep 2001 14:22:32 -0400 X-Mailer: KMail [version 1.2] MIME-Version: 1.0 Message-Id: <01090714223209.01035@anomaly.mit.edu> Content-Transfer-Encoding: 8bit Content-Transfer-Encoding: 8bit Subject: [Diffserv-interest] Automatic Class-of-Service Characterization? Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org Content-Transfer-Encoding: 8bit I'm a grad student at MIT/LCS, doing research into the automatic characterization of network flows - analyzing traffic in real time to attempt to "learn" about flows' classes of service (without having to know anything a priori about the protocols being used). Has anyone encountered similar research? I've been having a tough time finding any. (I figured this would be a good place to ask, since perhaps one application of such an engine would be to annotate packets automatically with a DS field.) Thanks, Jon -- =========================================================================== Jon Salz "One of the interesting initiatives we've taken Phone: 617-764-1255 in Washington, D.C., is we've got these vampire- AIM: JSalzAtMIT busting devices. A vampire is a--a cell deal you can plug in the wall to charge your cell phone." - Pres. George W. Bush, Denver, 8/14/2001 _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Fri Sep 7 14:34:07 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id OAA23419 for ; Fri, 7 Sep 2001 14:34:07 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id OAA22557; Fri, 7 Sep 2001 14:31:57 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id OAA22525 for ; Fri, 7 Sep 2001 14:31:55 -0400 (EDT) Received: from mail-gw1.hursley.ibm.com (mail-gw1.hursley.ibm.com [194.196.110.15]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id OAA23290 for ; Fri, 7 Sep 2001 14:30:27 -0400 (EDT) Received: from sp15en17.hursley.ibm.com (sp15at17.hursley.ibm.com [9.20.45.103]) by mail-gw1.hursley.ibm.com (AIX4.3/8.9.3/8.9.3) with ESMTP id TAA22828 for ; Fri, 7 Sep 2001 19:31:23 +0100 Received: from hursley.ibm.com ([9.29.3.173]) by sp15en17.hursley.ibm.com (AIX4.3/8.9.3/8.9.3) with ESMTP id TAA48906 for ; Fri, 7 Sep 2001 19:31:22 +0100 Message-ID: <3B9911C1.EC10B70B@hursley.ibm.com> Date: Fri, 07 Sep 2001 13:28:17 -0500 From: Brian E Carpenter Organization: IBM X-Mailer: Mozilla 4.76 [en] (Win98; U) X-Accept-Language: en,fr MIME-Version: 1.0 To: diffserv interest Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Transfer-Encoding: 7bit Subject: [Diffserv-interest] Diffserv mailing list admin Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org Content-Transfer-Encoding: 7bit People should be aware that this list contains more than 2000 names. This why all messages should be as short as possible and of course relevant to the working group's charter objectives. Some facts about the way the list is administered: Excessive bounces from an address (i.e. 20 or more) will cause that address to be disabled. There is a 25 kbyte limit on postings. Even the administrators cannot post messages beyond this limit. Remember, the IETF works in ASCII. At the moment, posting is restricted to list members as an anti-spam measure. Non-spam, non-trivia postings from non-members will be forwarded manually when time permits. To unsubscribe, go to http://www1.ietf.org/mailman/options/diffserv/ or in desperation, mail to diffserv-request@ietf.org (NOT to the list itself). Brian Carpenter acting temporary joint list admin (anyone else want to help with this?) _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Fri Sep 7 18:08:06 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id SAA29932 for ; Fri, 7 Sep 2001 18:08:01 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id RAA29977; Fri, 7 Sep 2001 17:53:28 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id RAA29948 for ; Fri, 7 Sep 2001 17:53:26 -0400 (EDT) Received: from mail-gw1.hursley.ibm.com (mail-gw1.hursley.ibm.com [194.196.110.15]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id RAA29584 for ; Fri, 7 Sep 2001 17:51:58 -0400 (EDT) Received: from sp15en17.hursley.ibm.com (sp15at17.hursley.ibm.com [9.20.45.103]) by mail-gw1.hursley.ibm.com (AIX4.3/8.9.3/8.9.3) with ESMTP id WAA39614; Fri, 7 Sep 2001 22:52:51 +0100 Received: from hursley.ibm.com ([9.29.3.173]) by sp15en17.hursley.ibm.com (AIX4.3/8.9.3/8.9.3) with ESMTP id WAA47298; Fri, 7 Sep 2001 22:52:50 +0100 Message-ID: <3B993FB5.10EA59A@hursley.ibm.com> Date: Fri, 07 Sep 2001 16:44:21 -0500 From: Brian E Carpenter Organization: IBM X-Mailer: Mozilla 4.76 [en] (Win98; U) X-Accept-Language: en,fr MIME-Version: 1.0 To: Christophe Gouault CC: Asim.Khan@vf.vodafone.co.uk, diffserv-interest@ietf.org References: <3B989183.943E1CED@6wind.com> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Transfer-Encoding: 7bit Subject: [Diffserv-interest] Re: [Diffserv] Behaviour of different flows in Diffserv network Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org Content-Transfer-Encoding: 7bit Christophe Gouault wrote: > > Asim.Khan@vf.vodafone.co.uk wrote: > > > Hi All, > > I have this question regarding a situation when the different flows are > > aggregated at the Diffserv network edge with similar constraints. They get > > allocated a particular DSCP to receice a treatment through the diffserv > > network. What would happen lets say that there is a mixture of TCP and UDP > > flows in that aggregate and they hit congestion. What effect would it have > > on those indivdual flows though part of an aggregate but under congestion > > situation TCP and UDP flow behave differently. > > > > Regards > > Asim > > Vodafone > > > > _______________________________________________ > > diffserv mailing list > > diffserv@ietf.org > > https://www1.ietf.org/mailman/listinfo/diffserv > > Archive: http://www2.ietf.org/mail-archive/working-groups/diffserv/current/maillist.html > > Hi Asim, > > IMHO, since TCP and UDP behave differently in congestion situations, they shouldn't be > aggregated in the same class of service. Only flows with similar constraints should be > aggregated. > > Christophe. That may be correct in theory, but in practice I am sure the situation Asim decribes will arise (for example if all of one customer's traffic gets the same SLA). What happens is exactly what happens today: you have effectively created a private Internet with TCP and non-TCP traffic competing. TCP will slow down and UDP will lose data. [switched this to the diffserv-interest list] Brian _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Wed Sep 12 09:56:03 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id JAA22070 for ; Wed, 12 Sep 2001 09:56:03 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id JAA27099; Wed, 12 Sep 2001 09:55:54 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id JAA27064 for ; Wed, 12 Sep 2001 09:55:52 -0400 (EDT) Received: from david.siemens.de (david.siemens.de [192.35.17.14]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id JAA22028 for ; Wed, 12 Sep 2001 09:55:23 -0400 (EDT) Received: from mail1.siemens.de (mail1.siemens.de [139.23.33.14]) by david.siemens.de (8.11.6/8.11.6) with ESMTP id f8CDtOW19394 for ; Wed, 12 Sep 2001 15:55:25 +0200 (MET DST) Received: from mail-y.mchp.siemens.de (mail-y.mchp.siemens.de [139.23.202.157]) by mail1.siemens.de (8.11.6/8.11.6) with ESMTP id f8CDtMx15534 for ; Wed, 12 Sep 2001 15:55:23 +0200 (MET DST) Received: from golf.mchp.siemens.de (golf [139.23.201.226]) by mail-y.mchp.siemens.de with ESMTP id f8CDtLcr001786 for ; Wed, 12 Sep 2001 15:55:21 +0200 (MET DST) Received: from mchp.siemens.de (mchp0819 [139.23.203.165]) by golf.mchp.siemens.de with ESMTP id f8CDtLEw016427 for ; Wed, 12 Sep 2001 15:55:21 +0200 (MET DST) Message-ID: <3B9F6886.BFA5220@mchp.siemens.de> Date: Wed, 12 Sep 2001 15:52:06 +0200 From: Karen Gray Reply-To: karen.gray.external@mchp.siemens.de Organization: Siemens X-Mailer: Mozilla 4.74 [en] (X11; U; Linux 2.2.16 i586) X-Accept-Language: en MIME-Version: 1.0 To: diffserv-interest@ietf.org Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Transfer-Encoding: 7bit Subject: [Diffserv-interest] Diffserv, AF, and EF question Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org Content-Transfer-Encoding: 7bit First, can someone please tell me how EF and AF are implemented in DiffServ? I know that there are 4 physical queues. Are these queues AF or EF? Second, does anyone know what the officially recommended scheduling method is for AF: RR, WRR, etc? Thank you, Karen Gray _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Wed Sep 12 11:19:39 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id LAA24445 for ; Wed, 12 Sep 2001 11:19:39 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id LAA29584; Wed, 12 Sep 2001 11:15:12 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id LAA29559 for ; Wed, 12 Sep 2001 11:15:11 -0400 (EDT) Received: from mail-gw1.hursley.ibm.com (mail-gw1.hursley.ibm.com [194.196.110.15]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id LAA24352 for ; Wed, 12 Sep 2001 11:14:41 -0400 (EDT) Received: from sp15en17.hursley.ibm.com (sp15at17.hursley.ibm.com [9.20.45.103]) by mail-gw1.hursley.ibm.com (AIX4.3/8.9.3/8.9.3) with ESMTP id QAA26310; Wed, 12 Sep 2001 16:14:13 +0100 Received: from hursley.ibm.com ([9.45.189.125]) by sp15en17.hursley.ibm.com (AIX4.3/8.9.3/8.9.3) with ESMTP id QAA46362; Wed, 12 Sep 2001 16:14:13 +0100 Message-ID: <3B9F7B87.1D1930A0@hursley.ibm.com> Date: Wed, 12 Sep 2001 10:13:11 -0500 From: Brian E Carpenter Organization: IBM X-Mailer: Mozilla 4.76 [en] (Win98; U) X-Accept-Language: en,fr MIME-Version: 1.0 To: karen.gray.external@mchp.siemens.de CC: diffserv-interest@ietf.org Subject: Re: [Diffserv-interest] Diffserv, AF, and EF question References: <3B9F6886.BFA5220@mchp.siemens.de> Content-Type: text/plain; charset=us-ascii Content-Transfer-Encoding: 7bit Content-Transfer-Encoding: 7bit Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org Content-Transfer-Encoding: 7bit Karen Gray wrote: > > First, can someone please tell me how EF and AF are implemented in > DiffServ? I know that there are 4 physical queues. No, there are as many queues as you happen to need acording to how many PHBs are configured on a given interface. In theory that is any number between 1 and 64 (meximum number of DSCP values). > Are these queues AF > or EF? Depends on local configuration > > Second, does anyone know what the officially recommended scheduling > method is for AF: RR, WRR, etc? There is no recommendation. It's an implementation decision, not a standards issue. The standard simply requires an implementation that meets the PHB group definition. If you look at the MIB, you will see that even the choice of scheduler is a configuration choice. Brian _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Mon Sep 17 06:06:51 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id GAA07220 for ; Mon, 17 Sep 2001 06:06:51 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id GAA25141; Mon, 17 Sep 2001 06:04:35 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id GAA25111 for ; Mon, 17 Sep 2001 06:04:33 -0400 (EDT) Received: from domino.netia.pl (domino.netia.pl [195.114.160.130]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id GAA07205 for ; Mon, 17 Sep 2001 06:04:30 -0400 (EDT) To: diffserv-interest@ietf.org X-Mailer: Lotus Notes Wydanie 5.0.4a 24 lipca 2000 Message-ID: From: "Andrzej Czerczak" Date: Mon, 17 Sep 2001 12:02:40 +0200 X-MIMETrack: Serialize by Router on WaWarNotes/HeadQ(Release 5.0.8 |June 18, 2001) at 2001-09-17 12:03:51 MIME-Version: 1.0 Content-type: text/plain; charset=us-ascii Subject: [Diffserv-interest] how to treat incoming traffic Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org Hi, I know the ECN-based proposals how to control TCP-based incoming traffic in DiffServ architecture. Has it at the moment a practical value? Why not to use egress TCP traffic policing? Could you point out on-going research how to control UDP incoming traffic if it conforms to the customer contract (receiver-based traffic control) in the diffserv architecture? rgrds Andrzej _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Mon Sep 17 13:27:15 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id NAA16797 for ; Mon, 17 Sep 2001 13:27:10 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id NAA08404; Mon, 17 Sep 2001 13:27:00 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id NAA08373 for ; Mon, 17 Sep 2001 13:26:58 -0400 (EDT) Received: from zcars0m9.ca.nortel.com (h157s242a129n47.user.nortelnetworks.com [47.129.242.157]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id NAA16793 for ; Mon, 17 Sep 2001 13:26:57 -0400 (EDT) Received: from zcars04f.ca.nortel.com (zcars04f.ca.nortel.com [47.129.242.57]) by zcars0m9.ca.nortel.com (8.11.0/8.11.0) with ESMTP id f8HHPFp17511 for ; Mon, 17 Sep 2001 13:25:15 -0400 (EDT) Message-Id: <200109171725.f8HHPFp17511@zcars0m9.ca.nortel.com> Received: from zcard00m.ca.nortel.com by zcars04f.ca.nortel.com; Mon, 17 Sep 2001 13:25:21 -0400 Received: from zcard00b.ca.nortel.com ([47.128.208.105]) by zcard00m.ca.nortel.com with SMTP (Microsoft Exchange Internet Mail Service Version 5.5.2653.13) id TBXL9852; Mon, 17 Sep 2001 13:25:22 -0400 Received: from wcars13p (wcars13p.ca.nortel.com [47.14.113.46]) by zcard00b.ca.nortel.com with SMTP (Microsoft Exchange Internet Mail Service Version 5.5.2653.13) id PLPJH1PQ; Mon, 17 Sep 2001 13:25:22 -0400 Date: Mon, 17 Sep 2001 13:25:19 -0400 (EDT) X-Sybari-Space: 00000000 00000000 00000000 From: "Jeff Norman" Reply-To: "Jeff Norman" Subject: fw:re:[Diffserv-interest] how to treat incoming traffic To: diffserv-interest@ietf.org X-Mailer: Rosa 3.0 X-Rosa-Trace: jnorman@wcars13p <47.14.113.46> MIME-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-ID: X-Orig: Content-Transfer-Encoding: 8bit X-MIME-Autoconverted: from quoted-printable to 8bit by optimus.ietf.org id NAA08374 Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org Content-Transfer-Encoding: 8bit Oops... forgot to include DiffServ-Int group in response... sorry. --Jeff ---forwarded-message----> >Subject: re:[Diffserv-interest] how to treat incoming traffic >Date: Sep 17 10:01 2001 >From: "Jeff Norman" >To: "Andrzej Czerczak" > > >Andrzej, > I think you may be confused with the main objective of using ECN in >TCP flows. The purpose of using ECN with TCP flows is to enable the >applications to react to network congestion with their TCP window >sizes without the need for TCP packets being dropped, which causes >time-outs and packets being re-transmitted (using up more router and >network resources). > >I would say that your statement of using egress TCP traffic policing >would not be used in place of ECN, but instead be used with it (to >determine the ECN of TCP packets) > >I have not heard of too many vendors implementing IP ECN into >their routers, nor have I heard a big push for it by customers in >the industry. > >I too would like to hear from others about what they think about >the practical value of IP ECN. > >I have not heard anything about research regarding controlling UDP flows, >but someone else may have. > >Best Regards, >--Jeff > >In message "[Diffserv-interest] how to treat incoming traffic", you write: > >>Hi, >>I know the ECN-based proposals how to control TCP-based incoming traffic >>in DiffServ architecture. Has it at the moment a practical value? Why not >>to use egress TCP traffic policing? >>Could you point out on-going research how to control UDP incoming traffic >>if it conforms to the customer contract (receiver-based traffic control) in >>the diffserv architecture? >> >>rgrds >>Andrzej >> >> >>_______________________________________________ >>Diffserv-interest mailing list >>Diffserv-interest@ietf.org >>http://www1.ietf.org/mailman/listinfo/diffserv-interest >> > _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Fri Sep 21 11:29:29 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id LAA28492 for ; Fri, 21 Sep 2001 11:29:28 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id LAA16321; Fri, 21 Sep 2001 11:25:11 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id LAA16290 for ; Fri, 21 Sep 2001 11:25:09 -0400 (EDT) Received: from infomail.es (ncc3.infomail.es [195.235.39.5]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id LAA28375 for ; Fri, 21 Sep 2001 11:25:45 -0400 (EDT) Received: from hp ([62.82.33.214]) by infomail.es (Tid InfoMail Exchanger v2.20) with SMTP id #1001085796.176490001; Fri, 21 Sep 2001 17:23:16 +0200 Message-ID: <020001c142b2$24298fc0$4220a8c0@hp> From: "Marck Gendra" To: Date: Fri, 21 Sep 2001 17:29:01 +0200 MIME-Version: 1.0 Content-Type: multipart/alternative; boundary="----=_NextPart_000_01FD_01C142C2.E7554BA0" X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.00.2615.200 X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2615.200 X-Infomail-Id: 1001085796.44F1010A81106E.45796 Subject: [Diffserv-interest] token bucket Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org This is a multi-part message in MIME format. ------=_NextPart_000_01FD_01C142C2.E7554BA0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable Hi, actually I'm making some tests with diffserv and Cisco routers. The tests consist of transmission of some video streams (UDP) and = varying the parameters of the Token Bucket (both parameters: average = rate and burst size). I would like to know if there must be any = correlation between the graphics obtained? Could anybody tell me where can i find detailed information on Token = Bucket algorithm and tests results related on Token Bucket? Thanks. ------=_NextPart_000_01FD_01C142C2.E7554BA0 Content-Type: text/html; charset="iso-8859-1" Content-Transfer-Encoding: quoted-printable
Hi,
 
actually I'm making some tests with = diffserv and=20 Cisco routers.
The tests consist of transmission of = some video=20 streams (UDP) and varying the parameters of the Token Bucket (both = parameters:=20 average rate and burst size). I would like to know if there must be any=20 correlation between the graphics obtained?
Could anybody tell me where can i find = detailed=20 information on Token Bucket algorithm and tests results related on Token = Bucket?
 
Thanks.
------=_NextPart_000_01FD_01C142C2.E7554BA0-- _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Mon Sep 24 09:02:40 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id JAA01514 for ; Mon, 24 Sep 2001 09:02:39 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id GAA17017; Mon, 24 Sep 2001 06:06:08 -0400 (EDT) Received: from eu1s006.globalknowledge.net ([213.181.145.234]) by optimus.ietf.org (8.9.1a/8.9.1) with SMTP id GAA16988 for ; Mon, 24 Sep 2001 06:06:05 -0400 (EDT) Received: FROM eu1s006.globalknowledge.net BY eu1s006.globalknowledge.net ; Mon Sep 24 12:02:36 2001 +0200 Received: by eu1s006.globalknowledge.net with Internet Mail Service (5.5.2653.19) id ; Mon, 24 Sep 2001 12:02:33 +0200 Message-ID: <2166DDC8B8ACD2119AA90008C709650B015DC8DE@fr1s001.globalknowledge.net> From: Kamel Sadani To: marck.gendra@upcnet.es Cc: diffserv-interest@ietf.org Date: Mon, 24 Sep 2001 11:48:49 +0200 MIME-Version: 1.0 X-Mailer: Internet Mail Service (5.5.2653.19) Content-Type: text/plain; charset="iso-8859-1" Subject: [Diffserv-interest] Token Bucket Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org I suggest you to use the following book " QoS and Traffic Management in IP and ATM Networks " that you could find at --> http://www.amazon.fr/exec/obidos/ASIN/0071349596/qid=1001325002/sr=1-6/ref=s r_1_0_6/171-9875715-7785050 Here, you'll get an accurate description of the Token Bucket mechanism (diagram, algo and statistical approach). This book is a very good help if you have to understand generic or specific aspects of QoS. If you are interested I can send you a PPT file describing the mechanism Token bucket with curves (plotted with Gnuplot) that are the result of simulations. Kamel Sadani _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Mon Sep 24 09:15:13 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id JAA04842 for ; Mon, 24 Sep 2001 09:15:09 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id JAA21074; Mon, 24 Sep 2001 09:14:44 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id JAA21046 for ; Mon, 24 Sep 2001 09:14:43 -0400 (EDT) Received: from lut.fi (stalk.cc.lut.fi [157.24.8.95]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id JAA04780 for ; Mon, 24 Sep 2001 09:14:35 -0400 (EDT) Received: from [157.24.25.96] (HELO elwe) by lut.fi (CommuniGate Pro SMTP 3.4.7) with SMTP id 895207; Mon, 24 Sep 2001 15:41:30 +0300 From: "Sergio Andreozzi" To: "Ns-Users@Isi. Edu" , "DS implementation mailing list" , "Diffserv-Interest mailing list" Date: Mon, 24 Sep 2001 15:39:35 +0300 Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook IMO, Build 9.0.2416 (9.0.2911.0) X-MimeOLE: Produced By Microsoft MimeOLE V5.50.4133.2400 Importance: Normal Content-Transfer-Encoding: 7bit Subject: [Diffserv-interest] MRED algorithms under DiffServ - s parameter computation Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org Content-Transfer-Encoding: 7bit Hi! MRED algorithms are based on RED. In this, to compute average queue lenght when a packet enters an empty queue, the s parameter have to be computed (s in the Floyd paper, 1/PTC in ns implementation - DiffServ module). m is "the number of packets that might have been transmitted by the gateway during the time that the line was free" and s is "a typical transmission time for a small packet". My question is: e.g. I have an outgoing link of 10 Mbit/s in a DiffServ enabled router. An AF PHB is configured to have 2 Mbit/s of bandwidth and a MRED mechanism is applied to it. How should I compute s? Should I consider 10 Mbit/s or 2 Mbit/s? (I guess 2 Mbit/s, but in ns 10 Mbit/s is considered). Thanks Sergio _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Mon Sep 24 09:45:40 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id JAA08890 for ; Mon, 24 Sep 2001 09:45:40 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id JAA22550; Mon, 24 Sep 2001 09:45:15 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id JAA22517 for ; Mon, 24 Sep 2001 09:45:14 -0400 (EDT) Received: from infomail.es (ncc4.infomail.es [195.235.39.6]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id JAA08816 for ; Mon, 24 Sep 2001 09:45:05 -0400 (EDT) Received: from nag ([195.235.39.55]) by infomail.es (Tid InfoMail Exchanger v2.20) with SMTP id #1001339094.250360001; Mon, 24 Sep 2001 15:44:54 +0200 From: JORGE MANRIQUE MARGALEJO To: sergio.andreozzi@lut.fi Cc: ns-users@isi.edu, dsimplementation@atnf.csiro.au, diffserv-interest@ietf.org Reply-To: JORGE MANRIQUE MARGALEJO Message-Id: <1001338640.26822@mail.infomail.es> Date: Mon, 24 Sep 2001 15:37:20 X-Mailer: Infom@il (correo con interfaz WEB) Mime-Version: 1.0 Content-Type: text/plain; charset=iso-8859-1 Content-Transfer-Encoding: 8bit X-Infomail-Id: 1001339094.61CC010A811075.59094 Content-Transfer-Encoding: 8bit Subject: [Diffserv-interest] Re: MRED algorithms under DiffServ - s parameter computation Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org Content-Transfer-Encoding: 8bit Hi Sergio, I have not deeply studied the code you're talking about. However, as you explain in your mail, it seems reasonable to use 2 Mbps instead of 10 Mbps. Even if the "typical transmission time for a small packet" is strictly size/10Mbps, if you're limiting the bandwith to 2 Mbps you're somehow increasing the actual trasnmision time for that traffic and slowing down the "virtual link" for that traffic. Using 2 Mbps sounds more logical to me but, as I say, I have not deeply studied the code so this is just my opinion. Regards, Jorge. ------------------------- Hi! MRED algorithms are based on RED. In this, to compute average queue lenght when a packet enters an empty queue, the s parameter have to be computed (s in the Floyd paper, 1/PTC in ns implementation - DiffServ module). m is "the number of packets that might have been transmitted by the gateway during the time that the line was free" and s is "a typical transmission time for a small packet". My question is: e.g. I have an outgoing link of 10 Mbit/s in a DiffServ enabled router. An AF PHB is configured to have 2 Mbit/s of bandwidth and a MRED mechanism is applied to it. How should I compute s? Should I consider 10 Mbit/s or 2 Mbit/s? (I guess 2 Mbit/s, but in ns 10 Mbit/s is considered). Thanks Sergio _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Mon Sep 24 10:47:01 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id KAA15029 for ; Mon, 24 Sep 2001 10:46:56 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id KAA24858; Mon, 24 Sep 2001 10:46:35 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id KAA24832 for ; Mon, 24 Sep 2001 10:46:34 -0400 (EDT) Received: from infomail.es (ncc3.infomail.es [195.235.39.5]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id KAA14979 for ; Mon, 24 Sep 2001 10:46:27 -0400 (EDT) Received: from hp ([193.153.7.163]) by infomail.es (Tid InfoMail Exchanger v2.20) with SMTP id #1001342669.067480001; Mon, 24 Sep 2001 16:44:29 +0200 Message-ID: <001d01c14508$30193da0$4220a8c0@hp> From: "Marck Gendra" To: "Kamel Sadani" Cc: References: <2166DDC8B8ACD2119AA90008C709650B015DC8DE@fr1s001.globalknowledge.net> Subject: RE: [Diffserv-interest] Token Bucket Date: Mon, 24 Sep 2001 16:49:25 +0200 MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook Express 5.00.2615.200 X-MimeOLE: Produced By Microsoft MimeOLE V5.00.2615.200 X-Infomail-Id: 1001342670.1A5C010A81106E.2670 Content-Transfer-Encoding: 7bit Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org Content-Transfer-Encoding: 7bit I would appreciate if you send me the graphics with th results of simulations because I'm very interestd. Thank you. ----- Original Message ----- From: Kamel Sadani To: Cc: Sent: Monday, September 24, 2001 11:48 AM Subject: [Diffserv-interest] Token Bucket > I suggest you to use the following book " QoS and Traffic Management in IP > and ATM Networks " that you could > find at --> > http://www.amazon.fr/exec/obidos/ASIN/0071349596/qid=1001325002/sr=1-6/ref=s > r_1_0_6/171-9875715-7785050 > sr_1_0_6/171-9875715-7785050> > > Here, you'll get an accurate description of the Token Bucket mechanism > (diagram, algo and statistical approach). > > This book is a very good help if you have to understand generic or specific > aspects of QoS. > > > If you are interested I can send you a PPT file describing the mechanism > Token bucket > with curves (plotted with Gnuplot) that are the result of simulations. > > > Kamel Sadani > > > _______________________________________________ > Diffserv-interest mailing list > Diffserv-interest@ietf.org > http://www1.ietf.org/mailman/listinfo/diffserv-interest > _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest From diffserv-interest-admin@ietf.org Tue Sep 25 04:27:17 2001 Received: from optimus.ietf.org (ietf.org [132.151.1.19] (may be forged)) by ietf.org (8.9.1a/8.9.1a) with ESMTP id EAA25545 for ; Tue, 25 Sep 2001 04:27:16 -0400 (EDT) Received: from optimus.ietf.org (localhost [127.0.0.1]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id EAA00200; Tue, 25 Sep 2001 04:26:57 -0400 (EDT) Received: from ietf.org (odin [132.151.1.176]) by optimus.ietf.org (8.9.1a/8.9.1) with ESMTP id EAA00168 for ; Tue, 25 Sep 2001 04:26:46 -0400 (EDT) Received: from lut.fi (stalk.cc.lut.fi [157.24.8.95]) by ietf.org (8.9.1a/8.9.1a) with ESMTP id EAA25541 for ; Tue, 25 Sep 2001 04:26:41 -0400 (EDT) Received: from [157.24.25.96] (HELO elwe) by lut.fi (CommuniGate Pro SMTP 3.4.7) with SMTP id 904336; Tue, 25 Sep 2001 11:26:44 +0300 From: "Sergio Andreozzi" To: "JORGE MANRIQUE MARGALEJO" Cc: , , Date: Tue, 25 Sep 2001 11:24:49 +0300 Message-ID: MIME-Version: 1.0 Content-Type: text/plain; charset="iso-8859-1" Content-Transfer-Encoding: 7bit X-Priority: 3 (Normal) X-MSMail-Priority: Normal X-Mailer: Microsoft Outlook IMO, Build 9.0.2416 (9.0.2911.0) Importance: Normal In-Reply-To: <1001338640.26822@mail.infomail.es> X-MimeOLE: Produced By Microsoft MimeOLE V5.50.4133.2400 Content-Transfer-Encoding: 7bit Subject: [Diffserv-interest] RE: MRED algorithms under DiffServ - s parameter computation Sender: diffserv-interest-admin@ietf.org Errors-To: diffserv-interest-admin@ietf.org X-Mailman-Version: 1.0 Precedence: bulk List-Id: Differentiated services general discussion X-BeenThere: diffserv-interest@ietf.org Content-Transfer-Encoding: 7bit > if you're limiting the > bandwith to 2 Mbps you're somehow increasing the actual > trasnmision time for that traffic and slowing down the "virtual > link" for that traffic. yes, you are right; but the parameter m is supposed to represent the number of packets that might have been transmitted during the idle time for the specific queue. Hence, the queue service rate should be used. If you have time check http://www.aciri.org/floyd/papers/early.pdf page 20-21 and dsredq.cc file (diffserv module, ns), function setPTC and enque. Bye Sergio _______________________________________________ Diffserv-interest mailing list Diffserv-interest@ietf.org http://www1.ietf.org/mailman/listinfo/diffserv-interest