lkml.org 
[lkml]   [2006]   [Jan]   [19]   [last100]   RSS Feed
Views: [wrap][no wrap]   [headers]  [forward] 
 
Messages in this thread
/
Date
From
SubjectRe: [patch 0/4] mm: de-skew page refcount
On Wed, Jan 18, 2006 at 11:27:13AM -0800, Linus Torvalds wrote:
>
>
> On Wed, 18 Jan 2006, Nick Piggin wrote:
> >
> > > So I disagree with this patch series. It has real downsides. There's a
> > > reason we have the offset.
> >
> > Yes, there is a reason, I detailed it in the changelog and got rid of it.
>
> And I'm not applying it. I'd be crazy to replace good code by code that is
> objectively _worse_.
>

And you're not? Damn.

> The fact that you _document_ that it's worse doesn't make it any better.
>
> The places that you improve (in the other patches) seem to have nothing at
> all to do with the counter skew issue, so I don't see the point.
>

You know, I believe you're right. I needed the de-skewing patch for
something unrelated and it seemed that it opened the possibility for
the following optimisations (ie. because we no longer touch a page
after its refcount goes to zero).

But actually it doesn't matter that we might touch page_count, only
that we not clear PageLRU. So the enabler is simply moving the
TestClearPageLRU after the get_page_testone.

So I'll respin the patches without the de-skewing and the series
will become much smaller and neater.

> So let me repeat: WHY DID YOU MAKE THE CODE WORSE?
>

You've never bothered me about that until now...

Thanks for the feedback!

Nick
-
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/

\
 
 \ /
  Last update: 2006-01-19 15:04    [W:0.061 / U:0.096 seconds]
©2003-2020 Jasper Spaans|hosted at Digital Ocean and TransIP|Read the blog|Advertise on this site