Compaction uses a watermark gap of (2UL << order) pages at various places and
it's not immediately obvious why. Abstract it through a compact_gap() wrapper
to create a single place with a thorough explanation.
Signed-off-by: Vlastimil Babka <vbabka@xxxxxxx>
Acked-by: Michal Hocko <mhocko@xxxxxxxx>
---
include/linux/compaction.h | 16 ++++++++++++++++
mm/compaction.c | 7 +++----
mm/vmscan.c | 4 ++--
3 files changed, 21 insertions(+), 6 deletions(-)
diff --git a/include/linux/compaction.h b/include/linux/compaction.h
index a6b3d5d2ae53..67a3372c4753 100644
--- a/include/linux/compaction.h
+++ b/include/linux/compaction.h
@@ -58,6 +58,22 @@ enum compact_result {
struct alloc_context; /* in mm/internal.h */
+/*
+ * Number of free order-0 pages that should be available above given watermark
+ * to make sure compaction has reasonable chance of not running out of free
+ * pages that it needs to isolate as migration target during its work.
+ */
+static inline unsigned long compact_gap(unsigned int order)
+{
+ /*
+ * Although all the isolations for migration are temporary, compaction
+ * may have up to 1 << order pages on its list and then try to split
+ * an (order - 1) free page. At that point, a gap of 1 << order might
+ * not be enough, so it's safer to require twice that amount.
+ */
+ return 2UL << order;
+}
+
#ifdef CONFIG_COMPACTION
extern int sysctl_compact_memory;
extern int sysctl_compaction_handler(struct ctl_table *table, int write,
diff --git a/mm/compaction.c b/mm/compaction.c
index 371760a85085..c1ce7c2abe05 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1395,11 +1395,10 @@ static enum compact_result __compaction_suitable(struct zone *zone, int order,
return COMPACT_PARTIAL;
/*
- * Watermarks for order-0 must be met for compaction. Note the 2UL.
- * This is because during migration, copies of pages need to be
- * allocated and for a short time, the footprint is higher
+ * Watermarks for order-0 must be met for compaction to be able to
+ * isolate free pages for migration targets.
*/
- watermark = low_wmark_pages(zone) + (2UL << order);
+ watermark = low_wmark_pages(zone) + compact_gap(order);
if (!__zone_watermark_ok(zone, 0, watermark, classzone_idx,
alloc_flags, wmark_target))
return COMPACT_SKIPPED;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 21d417ccff69..484ff05d5a8f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -2351,7 +2351,7 @@ static inline bool should_continue_reclaim(struct zone *zone,
* If we have not reclaimed enough pages for compaction and the
* inactive lists are large enough, continue reclaiming
*/
- pages_for_compaction = (2UL << sc->order);
+ pages_for_compaction = compact_gap(sc->order);
inactive_lru_pages = zone_page_state(zone, NR_INACTIVE_FILE);
if (get_nr_swap_pages() > 0)
inactive_lru_pages += zone_page_state(zone, NR_INACTIVE_ANON);
@@ -2478,7 +2478,7 @@ static inline bool compaction_ready(struct zone *zone, int order, int classzone_
*/
balance_gap = min(low_wmark_pages(zone), DIV_ROUND_UP(
zone->managed_pages, KSWAPD_ZONE_BALANCE_GAP_RATIO));
- watermark = high_wmark_pages(zone) + balance_gap + (2UL << order);
+ watermark = high_wmark_pages(zone) + balance_gap + compact_gap(order);
watermark_ok = zone_watermark_ok_safe(zone, 0, watermark, classzone_idx);
/*
--
2.8.4
--
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>