[openib-general] Re: ipoib_reap_ah question
Shirley Hello Roland, Is there any particular reason to use Shirley ipoib_reap_ah thread? Shirley In my tx_ring removal patch, I tested without Shirley ipoib_reap_ah work queue by simply adding kref_get(), Shirley kref_put() in ipoib_send(), and i didn't see any Shirley difference including performance. If there is no other Shirley risk, I will remove it to make it simple. Using kref_get() and kref_put() adds an atomic operation to the data path. You may not be measuring the cost but an atomic operation is just about the most expensive thing you can do. I think you should keep your patches simple -- one idea per patch. So if you want to experiment with both tx_ring removal and the reap_ah removal, keep in mind that they should be merged as separate patches. So you should probably develop them that way. - R. ___ 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
[openib-general] Re: ipoib_reap_ah question
Roland Dreier [EMAIL PROTECTED] wrote on 05/22/2006 09:58:13 AM: I think you should keep your patches simple -- one idea per patch. So if you want to experiment with both tx_ring removal and the reap_ah removal, keep in mind that they should be merged as separate patches. So you should probably develop them that way. - R. I will, thanks. If I seperate these two patches I will have to use last_send as atomic_t in tx_ring removal. 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
[openib-general] Re: ipoib_reap_ah question
Shirley I will, thanks. If I seperate these two patches I will Shirley have to use last_send as atomic_t in tx_ring removal. Why? And how does it help? ipoib never does any arithmetic on last_send so I don't see what changing it to atomic_t accomplishes. - R. ___ 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