Commit 5a1c84b4 authored by Mel Gorman's avatar Mel Gorman Committed by Linus Torvalds
Browse files

mm: remove reclaim and compaction retry approximations 

If per-zone LRU accounting is available then there is no point
approximating whether reclaim and compaction should retry based on pgdat
statistics.  This is effectively a revert of "mm, vmstat: remove zone
and node double accounting by approximating retries" with the difference
that inactive/active stats are still available.  This preserves the
history of why the approximation was retried and why it had to be
reverted to handle OOM kills on 32-bit systems.

Link: http://lkml.kernel.org/r/1469110261-7365-4-git-send-email-mgorman@techsingularity.net


Signed-off-by: default avatarMel Gorman <mgorman@techsingularity.net>
Acked-by: default avatarJohannes Weiner <hannes@cmpxchg.org>
Acked-by: default avatarMinchan Kim <minchan@kernel.org>
Cc: Michal Hocko <mhocko@suse.cz>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent bb4cc2be

include/linux/mmzone.h

+1 −0
Original line number Diff line number Diff line
@@ -116,6 +116,7 @@ enum zone_stat_item { 
	NR_ZONE_INACTIVE_FILE,

	NR_ZONE_ACTIVE_FILE,

	NR_ZONE_UNEVICTABLE,

	NR_ZONE_WRITE_PENDING,	/* Count of dirty, writeback and unstable pages */

	NR_MLOCK,		/* mlock()ed pages found and moved off LRU */

	NR_SLAB_RECLAIMABLE,

	NR_SLAB_UNRECLAIMABLE,

include/linux/swap.h

+1 −0
Original line number Diff line number Diff line
@@ -307,6 +307,7 @@ extern void lru_cache_add_active_or_unevictable(struct page *page, 
						struct vm_area_struct *vma);



/* linux/mm/vmscan.c */

extern unsigned long zone_reclaimable_pages(struct zone *zone);

extern unsigned long pgdat_reclaimable_pages(struct pglist_data *pgdat);

extern unsigned long try_to_free_pages(struct zonelist *zonelist, int order,

					gfp_t gfp_mask, nodemask_t *mask);

mm/compaction.c

+1 −19
Original line number Diff line number Diff line
@@ -1438,11 +1438,6 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, 
{

	struct zone *zone;

	struct zoneref *z;

	pg_data_t *last_pgdat = NULL;



	/* Do not retry compaction for zone-constrained allocations */

	if (ac->high_zoneidx < ZONE_NORMAL)

		return false;



	/*

	 * Make sure at least one zone would pass __compaction_suitable if we continue
@@ -1453,27 +1448,14 @@ bool compaction_zonelist_suitable(struct alloc_context *ac, int order, 
		unsigned long available;

		enum compact_result compact_result;



		if (last_pgdat == zone->zone_pgdat)

			continue;



		/*

		 * This over-estimates the number of pages available for

		 * reclaim/compaction but walking the LRU would take too

		 * long. The consequences are that compaction may retry

		 * longer than it should for a zone-constrained allocation

		 * request.

		 */

		last_pgdat = zone->zone_pgdat;

		available = pgdat_reclaimable_pages(zone->zone_pgdat) / order;



		/*

		 * Do not consider all the reclaimable memory because we do not

		 * want to trash just for a single high order allocation which

		 * is even not guaranteed to appear even if __compaction_suitable

		 * is happy about the watermark check.

		 */

		available = zone_reclaimable_pages(zone) / order;

		available += zone_page_state_snapshot(zone, NR_FREE_PAGES);

		available = min(zone->managed_pages, available);

		compact_result = __compaction_suitable(zone, order, alloc_flags,

				ac_classzone_idx(ac), available);

		if (compact_result != COMPACT_SKIPPED &&

mm/migrate.c

+2 −0
Original line number Diff line number Diff line
@@ -513,7 +513,9 @@ int migrate_page_move_mapping(struct address_space *mapping, 
		}

		if (dirty && mapping_cap_account_dirty(mapping)) {

			__dec_node_state(oldzone->zone_pgdat, NR_FILE_DIRTY);

			__dec_zone_state(oldzone, NR_ZONE_WRITE_PENDING);

			__inc_node_state(newzone->zone_pgdat, NR_FILE_DIRTY);

			__inc_zone_state(newzone, NR_ZONE_WRITE_PENDING);

		}

	}

	local_irq_enable();

mm/page-writeback.c

+5 −0
Original line number Diff line number Diff line
@@ -2462,6 +2462,7 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) 


		mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_DIRTY);

		__inc_node_page_state(page, NR_FILE_DIRTY);

		__inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);

		__inc_node_page_state(page, NR_DIRTIED);

		__inc_wb_stat(wb, WB_RECLAIMABLE);

		__inc_wb_stat(wb, WB_DIRTIED);
@@ -2483,6 +2484,7 @@ void account_page_cleaned(struct page *page, struct address_space *mapping, 
	if (mapping_cap_account_dirty(mapping)) {

		mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);

		dec_node_page_state(page, NR_FILE_DIRTY);

		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);

		dec_wb_stat(wb, WB_RECLAIMABLE);

		task_io_account_cancelled_write(PAGE_SIZE);

	}
@@ -2739,6 +2741,7 @@ int clear_page_dirty_for_io(struct page *page) 
		if (TestClearPageDirty(page)) {

			mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_DIRTY);

			dec_node_page_state(page, NR_FILE_DIRTY);

			dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);

			dec_wb_stat(wb, WB_RECLAIMABLE);

			ret = 1;

		}
@@ -2785,6 +2788,7 @@ int test_clear_page_writeback(struct page *page) 
	if (ret) {

		mem_cgroup_dec_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);

		dec_node_page_state(page, NR_WRITEBACK);

		dec_zone_page_state(page, NR_ZONE_WRITE_PENDING);

		inc_node_page_state(page, NR_WRITTEN);

	}

	unlock_page_memcg(page);
@@ -2839,6 +2843,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) 
	if (!ret) {

		mem_cgroup_inc_page_stat(page, MEM_CGROUP_STAT_WRITEBACK);

		inc_node_page_state(page, NR_WRITEBACK);

		inc_zone_page_state(page, NR_ZONE_WRITE_PENDING);

	}

	unlock_page_memcg(page);

	return ret;

CRA Git | Maintained and supported by SUSTech CRA and CCSE