Quoting Christoph Raisch <[EMAIL PROTECTED]>:
> Subject: Re: Re: [PATCH 2/6] [RFC] mthca kernel changes forresizeCQ
> 
> 
> I also prefer the idea that queue poll locking should be part of the device
> driver.

Seems to just be duplicated code at the moment.

> Especially on SMP systems there are interesting concepts around what else
> to do than just spinlock.

I'm not aware of any interesting concepts. What are they?
As Roland pointed out all existing drivers do polling under the lock.

-- 
Michael S. Tsirkin
Staff Engineer, Mellanox Technologies
_______________________________________________
openib-general mailing list
[email protected]
http://openib.org/mailman/listinfo/openib-general

To unsubscribe, please visit http://openib.org/mailman/listinfo/openib-general

Reply via email to