[PATCH 4/4] mm: use swap readahead at swapoff

[Konstantin Khlebnikov]

try_to_unuse() iterates over swap-entries sequentially,
thus readahead here will not hurt.

Test results:
Virtual machine: without patch 7 seconds, with patch 4 seconds.
Real hardware: without patch 100 seconds, with patch 70 seconds.

Signed-off-by: Konstantin Khlebnikov <khlebnikov@xxxxxxxxxx>
---
 mm/swapfile.c |    3 +--
 1 files changed, 1 insertions(+), 2 deletions(-)

diff --git a/mm/swapfile.c b/mm/swapfile.c
index d999f09..4c99689 100644
--- a/mm/swapfile.c
+++ b/mm/swapfile.c
@@ -1106,8 +1106,7 @@ static int try_to_unuse(unsigned int type)
 		 */
 		swap_map = &si->swap_map[i];
 		entry = swp_entry(type, i);
-		page = read_swap_cache_async(entry,
-					GFP_HIGHUSER_MOVABLE, NULL, 0);
+		page = swapin_readahead(entry, GFP_HIGHUSER_MOVABLE, NULL, 0);
 		if (!page) {
 			/*
 			 * Either swap_duplicate() failed because entry

--
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/