On Wed, Apr 27, 2011 at 1:25 AM, Minchan Kim <minchan.kim@xxxxxxxxx> wrote:
> There are some places to isolate lru page and I believe
> users of isolate_lru_page will be growing.
> The purpose of them is each different so part of isolated pages
> should put back to LRU, again.
>
> The problem is when we put back the page into LRU,
> we lose LRU ordering and the page is inserted at head of LRU list.
> It makes unnecessary LRU churning so that vm can evict working set pages
> rather than idle pages.
>
> This patch adds new filter mask when we isolate page in LRU.
> So, we don't isolate pages if we can't handle it.
> It could reduce LRU churning.
>
> This patch shouldn't change old behavior.
> It's just used by next patches.
>
> Cc: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx>
> Cc: Mel Gorman <mgorman@xxxxxxx>
> Cc: Rik van Riel <riel@xxxxxxxxxx>
> Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
> Signed-off-by: Minchan Kim <minchan.kim@xxxxxxxxx>
> ---
> Âinclude/linux/swap.h | Â Â3 ++-
> Âmm/compaction.c   Â|  Â2 +-
> Âmm/memcontrol.c   Â|  Â2 +-
> Âmm/vmscan.c     Â|  26 ++++++++++++++++++++------
> Â4 files changed, 24 insertions(+), 9 deletions(-)
>
> diff --git a/include/linux/swap.h b/include/linux/swap.h
> index 384eb5f..baef4ad 100644
> --- a/include/linux/swap.h
> +++ b/include/linux/swap.h
> @@ -259,7 +259,8 @@ extern unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *mem,
> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Âunsigned int swappiness,
> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Âstruct zone *zone,
> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Âunsigned long *nr_scanned);
> -extern int __isolate_lru_page(struct page *page, int mode, int file);
> +extern int __isolate_lru_page(struct page *page, int mode, int file,
> + Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â int not_dirty, int not_mapped);
> Âextern unsigned long shrink_all_memory(unsigned long nr_pages);
> Âextern int vm_swappiness;
> Âextern int remove_mapping(struct address_space *mapping, struct page *page);
> diff --git a/mm/compaction.c b/mm/compaction.c
> index 021a296..dea32e3 100644
> --- a/mm/compaction.c
> +++ b/mm/compaction.c
> @@ -335,7 +335,7 @@ static unsigned long isolate_migratepages(struct zone *zone,
> Â Â Â Â Â Â Â Â}
>
> Â Â Â Â Â Â Â Â/* Try isolate the page */
> - Â Â Â Â Â Â Â if (__isolate_lru_page(page, ISOLATE_BOTH, 0) != 0)
> + Â Â Â Â Â Â Â if (__isolate_lru_page(page, ISOLATE_BOTH, 0, 0, 0) != 0)
> Â Â Â Â Â Â Â Â Â Â Â Âcontinue;
>
> Â Â Â Â Â Â Â ÂVM_BUG_ON(PageTransCompound(page));
> diff --git a/mm/memcontrol.c b/mm/memcontrol.c
> index c2776f1..471e7fd 100644
> --- a/mm/memcontrol.c
> +++ b/mm/memcontrol.c
> @@ -1193,7 +1193,7 @@ unsigned long mem_cgroup_isolate_pages(unsigned long nr_to_scan,
> Â Â Â Â Â Â Â Â Â Â Â Âcontinue;
>
> Â Â Â Â Â Â Â Âscan++;
> - Â Â Â Â Â Â Â ret = __isolate_lru_page(page, mode, file);
> + Â Â Â Â Â Â Â ret = __isolate_lru_page(page, mode, file, 0, 0);
> Â Â Â Â Â Â Â Âswitch (ret) {
> Â Â Â Â Â Â Â Âcase 0:
> Â Â Â Â Â Â Â Â Â Â Â Âlist_move(&page->lru, dst);
> diff --git a/mm/vmscan.c b/mm/vmscan.c
> index b3a569f..71d2da9 100644
> --- a/mm/vmscan.c
> +++ b/mm/vmscan.c
> @@ -954,10 +954,13 @@ keep_lumpy:
> Â*
> Â* page: Â Â Â page to consider
> Â* mode: Â Â Â one of the LRU isolation modes defined above
> - *
> + * file: Â Â Â page be on a file LRU
> + * not_dirty: Âpage should be not dirty or not writeback
> + * not_mapped: page should be not mapped
> Â* returns 0 on success, -ve errno on failure.
> Â*/
> -int __isolate_lru_page(struct page *page, int mode, int file)
> +int __isolate_lru_page(struct page *page, int mode, int file,
> + Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â int not_dirty, int not_mapped)
> Â{
> Â Â Â Âint ret = -EINVAL;
>
> @@ -976,6 +979,12 @@ int __isolate_lru_page(struct page *page, int mode, int file)
> Â Â Â Âif (mode != ISOLATE_BOTH && page_is_file_cache(page) != file)
> Â Â Â Â Â Â Â Âreturn ret;
>
> + Â Â Â if (not_dirty)
> + Â Â Â Â Â Â Â if (PageDirty(page) || PageWriteback(page))
> + Â Â Â Â Â Â Â Â Â Â Â return ret;
> + Â Â Â if (not_mapped)
> + Â Â Â Â Â Â Â if (page_mapped(page))
> + Â Â Â Â Â Â Â Â Â Â Â return ret;
I should have fixed this return value.
Now caller regards -EINVAL with BUG.
I will fix it in next version.
--
Kind regards,
Minchan Kim
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxxx For more info on Linux MM,
see: http://www.linux-mm.org/ .
Fight unfair telecom internet charges in Canada: sign http://stopthemeter.ca/
Don't email: <a href