On Mon, Mar 03, 2008 at 11:44:07AM +0200, Pekka Enberg wrote:
quoted text
> Hi Nick,
> 
> On Mon, Mar 3, 2008 at 11:34 AM, Nick Piggin <npiggin@suse.de> wrote:
> >  SLUB should pack even small objects nicely into cachelines if that is what
> >  has been asked for. Use the same algorithm as SLAB for this.
> 
> The patches look good but this changelog is missing context. Why do we
> want to do this?

You're right, the changelog should be improved if/when it is merged.
Actually the context is discussed in another thread just now on lkml
if you are interested ("alloc_percpu() fails to allocate percpu data").

quoted text
> 
> On Mon, Mar 3, 2008 at 11:34 AM, Nick Piggin <npiggin@suse.de> wrote:
> >  @@ -1896,12 +1896,15 @@ static unsigned long calculate_alignment
> >          * specified alignment though. If that is greater
> >          * then use it.
> >          */
> 
> You might want to fix the above comment too.

Yes.

quoted text
> 
> >  -       if ((flags & SLAB_HWCACHE_ALIGN) &&
> >  -                       size > cache_line_size() / 2)
> >  -               return max_t(unsigned long, align, cache_line_size());
> >  +       if (flags & SLAB_HWCACHE_ALIGN) {
> >  +               unsigned long ralign = cache_line_size();
> >  +               while (size <= ralign / 2)
> >  +                       ralign /= 2;
> >  +               align = max(align, ralign);
> >  +       }
--
To unsubscribe from this list: send the line "unsubscribe netdev" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html