Enhance kmempowerd to determine situations where evacuating a region would prove
to be too costly or counter-productive, and ignore those regions for region
evacuation.
For example, if the region has a significant number of used pages (say more than
32), then evacuation will involve more work and might not be justifiable. Also,
compacting region 0 would be pointless, since that is the target of all our
compaction runs. Add these checks in the region-evacuator.
Signed-off-by: Srivatsa S. Bhat <srivatsa.b...@linux.vnet.ibm.com>
---
include/linux/mmzone.h | 2 ++
mm/compaction.c | 25 +++++++++++++++++++++++--
mm/internal.h | 2 ++
3 files changed, 27 insertions(+), 2 deletions(-)
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index 257afdf..f383cc8d4 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -84,6 +84,8 @@ static inline int get_pageblock_migratetype(struct page *page)
return get_pageblock_flags_group(page, PB_migrate, PB_migrate_end);
}
+#define MAX_MEMPWR_MIGRATE_PAGES 32
+
struct mem_region_list {
struct list_head *page_block;
unsigned long nr_free;
diff --git a/mm/compaction.c b/mm/compaction.c
index b56be89..41585b0 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1297,9 +1297,26 @@ void queue_mempower_work(struct pglist_data *pgdat,
struct zone *zone,
queue_kthread_work(&pgdat->mempower_worker, &mpwork->work);
}
+int should_evacuate_region(struct zone *z, struct zone_mem_region *region)
+{
+ unsigned long pages_in_use;
+
+ /* Don't try to evacuate region 0, since its the target of migration */
+ if (region == z->zone_regions)
+ return 0;
+
+ pages_in_use = region->present_pages - region->nr_free;
+
+ if (pages_in_use > 0 && pages_in_use <= MAX_MEMPWR_MIGRATE_PAGES)
+ return 1;
+
+ return 0;
+}
+
static void kmempowerd(struct kthread_work *work)
{
struct mempower_work *mpwork;
+ struct zone_mem_region *zmr;
struct zone *zone;
unsigned long flags;
int region_id;
@@ -1315,8 +1332,12 @@ repeat:
if (bitmap_empty(mpwork_mask, nr_zone_region_bits))
return;
- for_each_set_bit(region_id, mpwork_mask, nr_zone_region_bits)
- evacuate_mem_region(zone, &zone->zone_regions[region_id]);
+ for_each_set_bit(region_id, mpwork_mask, nr_zone_region_bits) {
+ zmr = &zone->zone_regions[region_id];
+
+ if (should_evacuate_region(zone, zmr))
+ evacuate_mem_region(zone, zmr);
+ }
spin_lock_irqsave(&mpwork->lock, flags);
diff --git a/mm/internal.h b/mm/internal.h
index 3fbc9f6..5b4658c 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -184,6 +184,8 @@ int compact_range(struct compact_control *cc, struct
aggression_control *ac,
void queue_mempower_work(struct pglist_data *pgdat, struct zone *zone,
int region_id);
+int should_evacuate_region(struct zone *z, struct zone_mem_region *region);
+
#endif
/*
--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majord...@vger.kernel.org
More majordomo info at http://vger.kernel.org/majordomo-info.html
Please read the FAQ at http://www.tux.org/lkml/
