Re: [RFC][PATCH] inactive_clean

[Peter Zijlstra <a.p.zijlstra@chello.nl>]

On Mon, 2006-06-19 at 12:58 -0700, Christoph Lameter wrote:
> On Mon, 19 Jun 2006, Rik van Riel wrote:
> 
> > On Mon, 19 Jun 2006, Christoph Lameter wrote:
> > > On Mon, 19 Jun 2006, Rik van Riel wrote:
> > > 
> > > > Not only swap.   Writable MAP_SHARED mmap has the same problem...
> > > 
> > > Writable MAP_SHARED is throttled by Peter Z. other patchset on page 
> > > dirtying. So the problem should have been solved at that level.
> > 
> > This new patch throttles both.   It might even make the other
> > one less needed - not sure...
> 
> Hmmm.. My counter patches add NR_ANON to count the number of anonymous 
> pages. These are all potentially dirty. If you throttle on NR_DIRTY + 
> NR_ANON then we may have the effect without this patch.

Sure, but what do you do to reach you threshold if there are not enough
mapped pages around to clean?

At that point the only thing left is to make sure some anonymous pages
become clean, that is write them out to swap and have them sit around in
the swap cache.

The next question is: 'which pages do I write out?', and there page
reclaim comes in; however are you only going to write out anonymous
pages and violate page order for file backed pages?

This train of thougth led to the proposed patch.

--
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>