aboutsummaryrefslogtreecommitdiff
path: root/mm/swap.c
diff options
context:
space:
mode:
authorMinchan Kim <minchan.kim@gmail.com>2011-03-22 16:32:54 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2011-03-22 17:44:04 -0700
commit278df9f451dc71dcd002246be48358a473504ad0 (patch)
tree3b79e956f2f0b9381f62518ff2fcf94df4ff9c3f /mm/swap.c
parent3f58a82943337fb6e79acfa5346719a97d3c0b98 (diff)
mm: reclaim invalidated page ASAP
invalidate_mapping_pages is very big hint to reclaimer. It means user doesn't want to use the page any more. So in order to prevent working set page eviction, this patch move the page into tail of inactive list by PG_reclaim. Please, remember that pages in inactive list are working set as well as active list. If we don't move pages into inactive list's tail, pages near by tail of inactive list can be evicted although we have a big clue about useless pages. It's totally bad. Now PG_readahead/PG_reclaim is shared. fe3cba17 added ClearPageReclaim into clear_page_dirty_for_io for preventing fast reclaiming readahead marker page. In this series, PG_reclaim is used by invalidated page, too. If VM find the page is invalidated and it's dirty, it sets PG_reclaim to reclaim asap. Then, when the dirty page will be writeback, clear_page_dirty_for_io will clear PG_reclaim unconditionally. It disturbs this serie's goal. I think it's okay to clear PG_readahead when the page is dirty, not writeback time. So this patch moves ClearPageReadahead. In v4, ClearPageReadahead in set_page_dirty has a problem which is reported by Steven Barrett. It's due to compound page. Some driver(ex, audio) calls set_page_dirty with compound page which isn't on LRU. but my patch does ClearPageRelcaim on compound page. In non-CONFIG_PAGEFLAGS_EXTENDED, it breaks PageTail flag. I think it doesn't affect THP and pass my test with THP enabling but Cced Andrea for double check. Signed-off-by: Minchan Kim <minchan.kim@gmail.com> Reported-by: Steven Barrett <damentz@liquorix.net> Reviewed-by: Johannes Weiner <hannes@cmpxchg.org> Acked-by: Rik van Riel <riel@redhat.com> Acked-by: Mel Gorman <mel@csn.ul.ie> Cc: Wu Fengguang <fengguang.wu@intel.com> Cc: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com> Cc: Nick Piggin <npiggin@kernel.dk> Cc: Andrea Arcangeli <aarcange@redhat.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm/swap.c')
-rw-r--r--mm/swap.c41
1 files changed, 38 insertions, 3 deletions
diff --git a/mm/swap.c b/mm/swap.c
index 1b9e4ebaffc..0a33714a7cb 100644
--- a/mm/swap.c
+++ b/mm/swap.c
@@ -354,26 +354,61 @@ void add_page_to_unevictable_list(struct page *page)
* head of the list, rather than the tail, to give the flusher
* threads some time to write it out, as this is much more
* effective than the single-page writeout from reclaim.
+ *
+ * If the page isn't page_mapped and dirty/writeback, the page
+ * could reclaim asap using PG_reclaim.
+ *
+ * 1. active, mapped page -> none
+ * 2. active, dirty/writeback page -> inactive, head, PG_reclaim
+ * 3. inactive, mapped page -> none
+ * 4. inactive, dirty/writeback page -> inactive, head, PG_reclaim
+ * 5. inactive, clean -> inactive, tail
+ * 6. Others -> none
+ *
+ * In 4, why it moves inactive's head, the VM expects the page would
+ * be write it out by flusher threads as this is much more effective
+ * than the single-page writeout from reclaim.
*/
static void lru_deactivate(struct page *page, struct zone *zone)
{
int lru, file;
+ bool active;
- if (!PageLRU(page) || !PageActive(page))
+ if (!PageLRU(page))
return;
/* Some processes are using the page */
if (page_mapped(page))
return;
+ active = PageActive(page);
+
file = page_is_file_cache(page);
lru = page_lru_base_type(page);
- del_page_from_lru_list(zone, page, lru + LRU_ACTIVE);
+ del_page_from_lru_list(zone, page, lru + active);
ClearPageActive(page);
ClearPageReferenced(page);
add_page_to_lru_list(zone, page, lru);
- __count_vm_event(PGDEACTIVATE);
+ if (PageWriteback(page) || PageDirty(page)) {
+ /*
+ * PG_reclaim could be raced with end_page_writeback
+ * It can make readahead confusing. But race window
+ * is _really_ small and it's non-critical problem.
+ */
+ SetPageReclaim(page);
+ } else {
+ /*
+ * The page's writeback ends up during pagevec
+ * We moves tha page into tail of inactive.
+ */
+ list_move_tail(&page->lru, &zone->lru[lru].list);
+ mem_cgroup_rotate_reclaimable_page(page);
+ __count_vm_event(PGROTATED);
+ }
+
+ if (active)
+ __count_vm_event(PGDEACTIVATE);
update_page_reclaim_stat(zone, page, file, 0);
}