> I noticed that the tasks queues still rely on the global tqueue_lock
> spinlock, instead of a per-taskqueue lock.
>
> The patch is virtually transparent for task queue users: all users
> except ieee1394 use DECLARE_TASK_QUEUE.
>
> I admit that the tqueue_lock isn't that often used (numbers from
> sgi's lockstat)
>
> * 10000 users/min during 'find / -xdev -uid 4711' (1.2% of all spinlock
> calls)
> * 60000 users/min during 'dd if=/dev/hda of=/dev/null' (~1.1% of all
> spinlock calls).
If there's no contention and nothing else changes, what is this
task supposed to fix?
Rik
-- Virtual memory is like a game you can't win; However, without VM there's truly nothing to lose...http://www.surriel.com/ http://www.conectiva.com/ http://distro.conectiva.com.br/
- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org Please read the FAQ at http://www.tux.org/lkml/