> On 10 Mar 2015, at 11:01, LOCHIN Emmanuel <[email protected]> wrote: > > So it means that a correct evaluation MUST takes into account the proportion > of data traffic from signalling traffic (pure ACK for instance) otherwise > performance measurements might be biaised. >
In the current version (01) of the draft, the traffic goes in one direction only. So a correct evaluation MUST indeed take into account the fact that only data traffic goes through the buffered ruled by an AQM. In the updated version (02) (which is not on-line because we just missed the cut-off to upload the version that assesses Wolfram’s comments), we will add a specific “both directions” case, where signalling and data packets are mixed. ------------------------------------------------------------------------------------------------------- 8.2. Bi-directional traffic Control packets such as DNS requests/responses, TCP SYNs/ACKs are small, but their loss can severely impact the application performance. The scenario proposed in this section will help in assessing whether the introduction of an AQM scheme increases the loss probability of these important packets. For this scenario, traffic MUST be generated in both downlink and uplink, such as defined in Section 3.1. These guidelines RECOMMEND to consider a mild congestion level and the traffic presented in section Section 7.2.2 in both directions. In this case, the metrics reported MUST be the same as in section Section 7.2 for each direction. The traffic mix presented in section Section 8.1 MAY also be generated in both direction. ------------------------------------------------------------------------------------------------------- Kind regards, Nicolas KUHN > Regards > > EK > > > Le Mardi 10 Mars 2015 08:52 CET, Nicolas Kuhn > <[email protected] <mailto:[email protected]>> > a écrit: > >> >> > Hi, > >> On 10 Mar 2015, at 08:28, LOCHIN Emmanuel <[email protected] >> <mailto:[email protected]>> wrote: >> >> Hi all, >> >> Reading section "12.4 Packet sizes and congestion notification", I'm >> wondering whether this should also apply to pure ack traffic? >> > > For this specific section, for the sake of consistency between the IETF > documents, > we refer to the “draft-ietf-aqm-recommendation“ document > [ https://datatracker.ietf.org/doc/draft-ietf-aqm-recommendation/ > <https://datatracker.ietf.org/doc/draft-ietf-aqm-recommendation/> ], > where it is said: > 1- in section "4.4 - AQM algorithms SHOULD respond to measured congestion, > not application profiles." > “ > Procedures for selecting packets to mark/drop > SHOULD observe the actual or projected time that a packet is in a > queue (bytes at a rate being an analog to time). When an AQM > algorithm decides whether to drop (or mark) a packet, it is > RECOMMENDED that the size of the particular packet should not be > taken into account [RFC7141]. > " > 2- in section "4.5. AQM algorithms SHOULD NOT be dependent on specific > transport protocol behaviours" > “ > AQM methods should be opaque to the choice of transport and application. > " > > IMHO, these two points infer that this would be applied for pure ack traffic > as well. > If changes need to be done on that aspect, it should be on the > “draft-ietf-aqm-recommendation“ document. > > Whatever happens, the “characterisation guidelines" document should be > consistent with the “recommendation document”, > and now that you mention this section, I am not sure that a discussion on the > packet sizes is needed in the “characterisation guidelines” document. > What do you think ? > > Kind regards, > > Nicolas > >> >> EL >> >> -- >> >> >> Emmanuel LOCHIN >> Professeur ISAE >> ISAE SUPAERO - Institut Supérieur de l'Aéronautique et de l'Espace >> 10 avenue Edouard Belin - BP 54032 - 31055 TOULOUSE CEDEX 4 FRANCE - >> http://www.isae-supaero.fr <http://www.isae-supaero.fr/> >> Tel +33 5 61 33 91 85 - Fax (+33) 5 61 33 83 30 >> Plan d'accès/Access map <http://plan.univ-toulouse.fr/#783> - Page >> personnelle <http://personnel.isae.fr/emmanuel-lochin> > > > -- > > > Emmanuel LOCHIN > Professeur ISAE > ISAE SUPAERO - Institut Supérieur de l'Aéronautique et de l'Espace > 10 avenue Edouard Belin - BP 54032 - 31055 TOULOUSE CEDEX 4 FRANCE - > http://www.isae-supaero.fr <http://www.isae-supaero.fr/> > Tel +33 5 61 33 91 85 - Fax (+33) 5 61 33 83 30 > Plan d'accès/Access map <http://plan.univ-toulouse.fr/#783> - Page > personnelle <http://personnel.isae.fr/emmanuel-lochin>
_______________________________________________ aqm mailing list [email protected] https://www.ietf.org/mailman/listinfo/aqm
