Re: [RFC] some page can't be migrated

[Shaohua Li]

On Fri, 2008-01-25 at 14:03 +1100, Nick Piggin wrote:
> On Wednesday 23 January 2008 17:22, Shaohua Li wrote:
> > Anonymous page might have fs-private metadata, the page is truncated. As
> > the page hasn't mapping, page migration refuse to migrate the page. It
> > appears the page is only freed in page reclaim and if zone watermark is
> > low, the page is never freed, as a result migration always fail. I
> > thought we could free the metadata so such page can be freed in
> > migration and make migration more reliable?
> 
> Anonymous pages should not have fs-private metadata.
> 
> Orphaned pages I guess you mean?
yes, maybe, but the comments in truncate_complete_page called the page
anonymous.
> They should not be accessable via
> the pagecache or the page tables, so how do they keep tangling up
> migration? Where/how is migration finding these pages?!
the page is still in lru list. Memory hot remove will try to migrate the
page.

Thanks,
Shaohua

> >
> > diff --git a/mm/migrate.c b/mm/migrate.c
> > index 6a207e8..6bc38f7 100644
> > --- a/mm/migrate.c
> > +++ b/mm/migrate.c
> > @@ -633,6 +633,17 @@ static int unmap_and_move(new_page_t get_new_page,
> > unsigned long private, goto unlock;
> >  		wait_on_page_writeback(page);
> >  	}
> > +
> > +	/*
> > +	 * See truncate_complete_page(). Anonymous page might have
> > +	 * fs-private metadata, the page is truncated. Such page can't be
> > +	 * migrated. Try to free metadata, so the page can be freed.
> > +	 */
> > +	if (!page->mapping && !PageAnon(page) && PagePrivate(page)) {
> > +		try_to_release_page(page, GFP_KERNEL);
> > +		goto unlock;
> > +	}
> > +
> >  	/*
> >  	 * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
> >  	 * we cannot notice that anon_vma is freed while we migrates a page.
> >
> >
> > --

--
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/