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.

Regards

EK


Le Mardi 10 Mars 2015 08:52 CET, Nicolas Kuhn 
<[email protected]> a écrit:
  Hi, On 10 Mar 2015, at 08:28, LOCHIN Emmanuel <[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/ ], 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
Tel +33 5 61 33 91 85 - Fax (+33) 5 61 33 83 30
Plan d'accès/Access map - Page personnelle


--
  
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
Tel +33 5 61 33 91 85 - Fax (+33) 5 61 33 83 30
Plan d'accès/Access map -  Page personnelle
_______________________________________________
aqm mailing list
[email protected]
https://www.ietf.org/mailman/listinfo/aqm

Reply via email to