Ok ... so a spinlock (task_lock) costs one barrier and one atomic more
than an rcu_read_lock (on a preempt kernel where both spinlock and
rcu_read_lock cost a preempt), or something like that.
Thanks, Nick.
--
I won't rest till it's the best ...
Programmer, Linux Scalability
Paul Jackson <[email protected]> 1.925.600.0401
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to [email protected]
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
- References:
- [PATCH]: Clean up of __alloc_pages
- From: "Rohit, Seth" <[email protected]>
- Re: [PATCH]: Clean up of __alloc_pages
- From: Paul Jackson <[email protected]>
- Re: [PATCH]: Clean up of __alloc_pages
- From: Nick Piggin <[email protected]>
- Re: [PATCH]: Clean up of __alloc_pages
- From: Andi Kleen <[email protected]>
- Re: [PATCH]: Clean up of __alloc_pages
- From: Paul Jackson <[email protected]>
- Re: [PATCH]: Clean up of __alloc_pages
- From: Nick Piggin <[email protected]>
- Re: [PATCH]: Clean up of __alloc_pages
- From: Paul Jackson <[email protected]>
- Re: [PATCH]: Clean up of __alloc_pages
- From: Nick Piggin <[email protected]>
- [PATCH]: Clean up of __alloc_pages
- Prev by Date: Re: [PATCH] slightly enhance cross builds
- Next by Date: Re: negative timeout can be set up by setsockopt system call
- Previous by thread: Re: [PATCH]: Clean up of __alloc_pages
- Next by thread: Re: [PATCH]: Clean up of __alloc_pages
- Index(es):
 |