[Ns-developers] Importance of processing delays accounting.

[Nicola Baldo]

Hi Elena,

sorry for the late reply. Please find a few comments below.

On 08/04/2010 02:30 PM, Elena Buchatskaya wrote:
> Generally speaking none of the ns-3 models account for processing
> delays. The necessity of adding random delay in Wi-Fi module has
> already been discussed (see bug 912), but I think the more general
> solution is desirable. We need to model  non-deterministic processing
> delays at various OSI layers. I propose to add a adjustable delay:
> 1) between the IP  and Wi-Fi MAC layers to accommodate the processing
> time at the IP layer. This is the time needed to to look up routes in
> a routing table, to recompute the checksum of the IP header as well as
> the time needed to prepare the packet for further transmission.
> 2) between MAC and PHY layers to accommodate the processing time at
> the MAC layer and time required to copy packet for kernel space to the
> device.

I agree with modeling the time required to copy packet from kernel space 
to the device; I think the right point to do it is upon enqueueing the 
packet onto DcaTxop.

However, I am not sure about adding a random delay between the MAC and 
the PHY. In my experience, most of the delay at the MacLow level and 
below is due to the processing done by the MAC (e.g., CRC calculation), 
is tightly bounded by the standard (e.g., by SIFS timing) and in 
commercial devices it is almost deterministic (some colleagues of mine 
measured a standard deviation below one microsecond for the delay 
between a DATA packet and its ACK). What would be the purpose of 
introducing such a model in ns-3?

Regards,

Nicola