Re: [RFC] unify semaphore implementations

From: Benjamin LaHaise
Date: Thu Apr 28 2005 - 14:01:46 EST


On Thu, Apr 28, 2005 at 11:48:09AM -0700, James Bottomley wrote:
> Could you come up with a less monolithic way to share this so that we
> can still do a spinlock semaphore implementation instead of an atomic op
> based one?

As I read the code, it doesn't make a difference: parisc will take a
spin lock within the atomic operation and then release it, which makes
the old fast path for the semaphores and the new fast path pretty much
equivalent (they both take and release one spinlock). The only extra
cost is the address computation for the spinlock. If there is contention
for the atomic spinlocks, then parisc can increase the number of buckets
in their hashed spinlocks.

-ben
--
"Time is what keeps everything from happening all at once." -- John Wheeler
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/