Prev: libata: take advantage of cmwq and remove concurrency limitations
Next: async: use workqueue for worker pool
From: Tejun Heo on 6 Jul 2010 10:30
On 07/06/2010 04:22 PM, Christoph Lameter wrote:
> On Tue, 29 Jun 2010, Tejun Heo wrote:
>
>> What alignment maintenance? Are you talking about the UP code? If
>> you're talking about the UP code, the ugliness there is because the
>> current UP __alloc_percpu() can't honor the alignment parameter.
>
> Why do we need alignment on UP? Cachelines typically dont bounce if a
> single processor accesses the data.

Because work->data is multiplexed with pointer and flag bits, so the
targets of the pointer (cwq's) need to be aligned so that the lower
part of the pointer always stays zero.

Thanks.

--
tejun
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
From: Christoph Lameter on 6 Jul 2010 10:30
On Tue, 29 Jun 2010, Tejun Heo wrote:

> What alignment maintenance? Are you talking about the UP code? If
> you're talking about the UP code, the ugliness there is because the
> current UP __alloc_percpu() can't honor the alignment parameter.

Why do we need alignment on UP? Cachelines typically dont bounce if a
single processor accesses the data.

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo(a)vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
First  |  Prev  | 
Pages: 1 2 3
Prev: libata: take advantage of cmwq and remove concurrency limitations
Next: async: use workqueue for worker pool