Re: [RFC][PATCH] radix-tree based page_cgroup. [7/7] per cpu fast lookup

["minchan Kim" <barrioskmc@gmail.com>]

On Wed, Feb 27, 2008 at 8:37 AM, KAMEZAWA Hiroyuki
<kamezawa.hiroyu@jp.fujitsu.com> wrote:
> On Tue, 26 Feb 2008 22:26:40 +0900
>
> "minchan Kim" <barrioskmc@gmail.com> wrote:
>
>
>
> > >  -struct page_cgroup *get_page_cgroup(struct page *page, gfp_t gfpmask)
>  > >  +struct page_cgroup *__get_page_cgroup(struct page *page, gfp_t gfpmask)
>  > >   {
>  > >         struct page_cgroup_root *root;
>  > >         struct page_cgroup *pc, *base_addr;
>  > >  @@ -96,8 +110,14 @@ retry:
>  > >         pc = radix_tree_lookup(&root->root_node, idx);
>  > >         rcu_read_unlock();
>  > >
>  > >  +       if (pc) {
>  > >  +               if (!in_interrupt())
>  > >  +                       save_result(pc, idx);
>  > >  +       }
>  > >  +
>  >
>  > I didn't look through mem_control's patches yet.
>  > Please understand me if my question might be foolish.
>  >
>  > why do you prevent when it happen in interrupt context ?
>  > Do you have any reason ?
>  >
>  looking up isn't done under irq disable but under preempt disable.

I can't understand your point.
Is that check is really necessary if save_result function use
get_cpu_var and put_cpu_var in save_result ?

>  Thanks,
>  -Kame
>
>



-- 
Thanks,
barrios

--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@kvack.org.  For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@kvack.org"> email@kvack.org </a>