Re: [PATCH] mm: fix page-faults detection in swap-token logic

[Rik van Riel]

On 08/29/2011 07:06 PM, Andrew Morton wrote:
> On Sat, 27 Aug 2011 12:32:01 +0300
> Konstantin Khlebnikov<khlebnikov@xxxxxxxxxx>  wrote:
>
> > After commit v2.6.36-5896-gd065bd8 "mm: retry page fault when blocking on disk transfer"
> > we usually wait in page-faults without mmap_sem held, so all swap-token logic was broken,
> > because it based on using rwsem_is_locked(&mm->mmap_sem) as sign of in progress page-faults.
>
> If I'm interpreting this correctly, the thrash-handling logic has been
> effectively disabled for a year and nobody noticed.
>
> > This patch adds to mm_struct atomic counter of in progress page-faults for mm with swap-token.
>
> We desperately need to delete some code from mm/.  This seems like a
> great candidate.  Someone prove me wrong?

You are absolutely right.  The swap token code broke without
anyone noticing, and there is no good way to integrate it with
cgroups naturalization...

I'll send a patch to remove the swap token code.

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