Roland Dreier <[EMAIL PROTECTED]> wrote on 04/19/2006 02:34:24 PM:
> Shirley> OK. I am going to split the patch without splitting CQ
> Shirley> first. WC handler is called in the interrupt context, it
> Shirley> is a myth to have bidirectional performance improvement
> Shirley> with splitting CQ. More investigation is needed.
>
> But you did see performance improvement on mthca, right? The reason
> for that is what I would like to understand.
>
> - R.
Yes. We did see the performance improvement on mthca. The better
way to understand the performance improvement maybe profiling
the kernel.
Also I am working on removal tx_ring, which requires CQ to be splited
to remove recv WC wiki flag IPOIB_OP_RECV.
Thanks
Shirley Ma
IBM Linux Technology Center
15300 SW Koll Parkway
Beaverton, OR 97006-6063
Phone(Fax): (503) 578-7638
_______________________________________________ openib-general mailing list openib-general@openib.org http://openib.org/mailman/listinfo/openib-general
To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general
