[vortex] What are the issues related to increasing Rx ring size ?

Amitava Biswas amita_bi at ece.concordia.ca
Thu Sep 23 06:08:30 PDT 2004


Hi,
I have gone through the source code of 3c905 driver.
I want to use this driver under a situation when packets arrive in bursts (few hundered to say one thousand small (64Byte) packets in one burst). I want to avoid loss of packets, so I want to increase the receive ring size. I have the following questions-

1) Assuming that I have lots of RAM and take care of the protocol and socket processing layers (increase the socket buffer sizes there too, by making changes in kernel and libraries), 
I also assume that lots of "sk_buff"s have already been preallocated so that the interrupt portion of code does not get performance hits due to on the fly alloc, and I also assume that rest of the code is fast enough to respond to fast interrupt rates.

Can I increase the Rx ring size to 1024 ? If not why ? What is the limit ? 

****Does the NIC design aspects limits this ?

To be specific what is the maximum number of receive descriptors the NIC (say 3c905B-TX) can handle ? I understand the NIC firmware has been designed in such way that it can operate on, say maximum  "n" descriptors, till they are cleared by the driver interrupt handler (is this correct ?).

***What is the value of "n" for a typical 3c9XX NIC ?

Perhaps this simple information is available in the NIC specs, which is not a public domain doc. I am expecting that some driver writer has this, and can kindly share this information or the document itself or a tip on how to get it from 3 com (I would be grateful).


2) What are the other issues which may be the hurdles or constraints  to the driver operation with large Rx ring size ? These may be both - system / resource constraints and performance constraints.

Thanks for your time.

Regards
Amitava Biswas
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.scyld.com/pipermail/vortex/attachments/20040923/e4c68b26/attachment.html


More information about the vortex mailing list