commit 0cee34fd72c582b4f8ad8ce00645b75fb4168199 upstream.
Stable note: Not tracked on Bugzilla. THP and compaction was found to
aggressively reclaim pages and stall systems under different
situations that was addressed piecemeal over time.
If compaction can proceed for a given zone, shrink_zones() does not
reclaim any more pages from it. After commit [e0c2327: vmscan: abort
reclaim/compaction if compaction can proceed], do_try_to_free_pages()
tries to finish as soon as possible once one zone can compact.
This was intended to prevent slabs being shrunk unnecessarily but
there are side-effects. One is that a small zone that is ready for
compaction will abort reclaim even if the chances of successfully
allocating a THP from that zone is small. It also means that reclaim
can return too early even though sc->nr_to_reclaim pages were not
reclaimed.
This partially reverts the commit until it is proven that slabs are
really being shrunk unnecessarily but preserves the check to return
1 to avoid OOM if reclaim was aborted prematurely.
[aarcange@xxxxxxxxxx: This patch replaces a revert from Andrea]
Signed-off-by: Mel Gorman <mgorman@xxxxxxx>
Reviewed-by: Rik van Riel <riel@xxxxxxxxxx>
Cc: Andrea Arcangeli <aarcange@xxxxxxxxxx>
Cc: Minchan Kim <minchan.kim@xxxxxxxxx>
Cc: Dave Jones <davej@xxxxxxxxxx>
Cc: Jan Kara <jack@xxxxxxx>
Cc: Andy Isaacson <adi@xxxxxxxxxxxxx>
Cc: Nai Xia <nai.xia@xxxxxxxxx>
Cc: Johannes Weiner <jweiner@xxxxxxxxxx>
Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Linus Torvalds <torvalds@xxxxxxxxxxxxxxxxxxxx>
Signed-off-by: Mel Gorman <mgorman@xxxxxxx>
---
mm/vmscan.c | 19 +++++++++----------
1 file changed, 9 insertions(+), 10 deletions(-)
diff --git a/mm/vmscan.c b/mm/vmscan.c
index f109f2d..bc31f32 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2129,7 +2129,8 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc)
*
* This function returns true if a zone is being reclaimed for a costly
* allocation and compaction is ready to begin. This indicates to the caller
- * that it should retry the allocation or fail.
+ * that it should consider retrying the allocation instead of
+ * further reclaim.
*/
static bool shrink_zones(int priority, struct zonelist *zonelist,
struct scan_control *sc)
@@ -2138,7 +2139,7 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
struct zone *zone;
unsigned long nr_soft_reclaimed;
unsigned long nr_soft_scanned;
- bool should_abort_reclaim = false;
+ bool aborted_reclaim = false;
for_each_zone_zonelist_nodemask(zone, z, zonelist,
gfp_zone(sc->gfp_mask), sc->nodemask) {
@@ -2164,7 +2165,7 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
* allocations.
*/
if (compaction_ready(zone, sc)) {
- should_abort_reclaim = true;
+ aborted_reclaim = true;
continue;
}
}
@@ -2186,7 +2187,7 @@ static bool shrink_zones(int priority, struct zonelist *zonelist,
shrink_zone(priority, zone, sc);
}
- return should_abort_reclaim;
+ return aborted_reclaim;
}
static bool zone_reclaimable(struct zone *zone)
@@ -2240,7 +2241,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
struct zoneref *z;
struct zone *zone;
unsigned long writeback_threshold;
- bool should_abort_reclaim;
+ bool aborted_reclaim;
get_mems_allowed();
delayacct_freepages_start();
@@ -2252,9 +2253,7 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist,
sc->nr_scanned = 0;
if (!priority)
disable_swap_token(sc->mem_cgroup);
- should_abort_reclaim = shrink_zones(priority, zonelist, sc);
- if (should_abort_reclaim)
- break;
+ aborted_reclaim = shrink_zones(priority, zonelist, sc);
/*
* Don't shrink slabs when reclaiming memory from
@@ -2320,8 +2319,8 @@ out:
if (oom_killer_disabled)
return 0;
- /* Aborting reclaim to try compaction? don't OOM, then */
- if (should_abort_reclaim)
+ /* Aborted reclaim to try compaction? don't OOM, then */
+ if (aborted_reclaim)
return 1;
/* top priority shrink_zones still had more to do? don't OOM, then */
--
1.7.9.2
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>