[openib-general] Re: openib-general Digest, Vol 22, Issue 114

[Shirley Ma]

Roland Dreier <rdreier at cisco.com> wrote on 04/18/2006 03:06:33 PM:

> And actually it argues against splitting the CQ, because having one CQ
> increases the number of CQ entries that we have a chance to poll at
> any one time, by lumping send and receive completions together...
> 
>  - R.

The send needs to obtain tx_lock to handle send wc. Receive doesn't 
need to. That might explain some of the performance. 
I have tried to remove tx_lock in send wc handler by removeing tx_ring. 
It did increase the send speed. I hit an ehca problem, the test couldn't 
move on.

And splitting CQ is really benefit the duplex throughput.

We are doing more testing now to dig out more info.

Thanks
Shirley Ma
IBM Linux Technology Center
15300 SW Koll Parkway
Beaverton, OR 97006-6063
Phone(Fax): (503) 578-7638

-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.openfabrics.org/pipermail/general/attachments/20060418/7b695f70/attachment.html>