Re: [PATCH] nbd driver for 2.5+: fix for module removal & new block device layer

[Jens Axboe]

On Sat, Jun 21 2003, Lou Langholtz wrote:
> >	b) you definitely don't have to use separate queue locks.  The
> >thing will work fine with spinlock being shared and I doubt that there
> >will be any noticable extra contention.
> >
> Probably not noticeable no.

The approach you took is probably _worse_ than a single lock, since you
don't even cache align the locks. I'd say just keep the single nbd_lock
and use that in all queues, seperate locks are a questionable win but do
take up extra space.

-- 
Jens Axboe