On Thu, 10 May 2007, Pekka Enberg wrote:
> Ok. I would appreciate any kind of heads-up when you're ready to eat
> these patches again. ;-)
If you have some more spare cycles: Try to extend this
to get rid of the inode constructors in the other fs as well?
(And if you have even more time and are
On 5/9/07, Andrew Morton <[EMAIL PROTECTED]> wrote:
ext2 has no truncate_mutex.
I think it does:
- mutex_init(&ei->truncate_mutex);
- inode_init_once(&ei->vfs_inode);
- }
-}
And fs/ext2/super.c:init_once() from 2.6.21-mm2 says:
mutex_init(&ei-
On 5/10/07, Andrew Morton <[EMAIL PROTECTED]> wrote:
On Sat, 5 May 2007 12:57:46 +0300 (EEST)
Pekka J Enberg <[EMAIL PROTECTED]> wrote:
> From: Pekka Enberg <[EMAIL PROTECTED]>
>
> As alloc_inode() touches the same cache line as init_once(), we gain
> nothing from using slab constructors.
>
> Cc
On Sat, 5 May 2007 12:57:46 +0300 (EEST)
Pekka J Enberg <[EMAIL PROTECTED]> wrote:
> From: Pekka Enberg <[EMAIL PROTECTED]>
>
> As alloc_inode() touches the same cache line as init_once(), we gain
> nothing from using slab constructors.
>
> Cc: Stephen C. Tweedie <[EMAIL PROTECTED]>
> Cc: Andrea
From: Pekka Enberg <[EMAIL PROTECTED]>
As alloc_inode() touches the same cache line as init_once(), we gain
nothing from using slab constructors.
Cc: Stephen C. Tweedie <[EMAIL PROTECTED]>
Cc: Andreas Dilger <[EMAIL PROTECTED]>
Cc: Christoph Lameter <[EMAIL PROTECTED]>
Signed-off-by: Pekka Enberg
5 matches
Mail list logo
