Commit c4a25635 authored by Mel Gorman's avatar Mel Gorman Committed by Linus Torvalds
Browse files

mm: move vmscan writes and file write accounting to the node 

As reclaim is now node-based, it follows that page write activity due to
page reclaim should also be accounted for on the node.  For consistency,
also account page writes and page dirtying on a per-node basis.

After this patch, there are a few remaining zone counters that may appear
strange but are fine.  NUMA stats are still per-zone as this is a
user-space interface that tools consume.  NR_MLOCK, NR_SLAB_*,
NR_PAGETABLE, NR_KERNEL_STACK and NR_BOUNCE are all allocations that
potentially pin low memory and cannot trivially be reclaimed on demand.
This information is still useful for debugging a page allocation failure
warning.

Link: http://lkml.kernel.org/r/1467970510-21195-21-git-send-email-mgorman@techsingularity.net


Signed-off-by: default avatarMel Gorman <mgorman@techsingularity.net>
Acked-by: default avatarVlastimil Babka <vbabka@suse.cz>
Acked-by: default avatarMichal Hocko <mhocko@suse.com>
Cc: Hillf Danton <hillf.zj@alibaba-inc.com>
Acked-by: default avatarJohannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Minchan Kim <minchan@kernel.org>
Cc: Rik van Riel <riel@surriel.com>
Signed-off-by: default avatarAndrew Morton <akpm@linux-foundation.org>
Signed-off-by: default avatarLinus Torvalds <torvalds@linux-foundation.org>
parent 11fb9989

include/linux/mmzone.h

+4 −4
Original line number Diff line number Diff line
@@ -122,10 +122,6 @@ enum zone_stat_item { 
	NR_KERNEL_STACK,

	/* Second 128 byte cacheline */

	NR_BOUNCE,

	NR_VMSCAN_WRITE,

	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */

	NR_DIRTIED,		/* page dirtyings since bootup */

	NR_WRITTEN,		/* page writings since bootup */

#if IS_ENABLED(CONFIG_ZSMALLOC)

	NR_ZSPAGES,		/* allocated in zsmalloc */

#endif
@@ -165,6 +161,10 @@ enum node_stat_item { 
	NR_SHMEM_PMDMAPPED,

	NR_ANON_THPS,

	NR_UNSTABLE_NFS,	/* NFS unstable pages */

	NR_VMSCAN_WRITE,

	NR_VMSCAN_IMMEDIATE,	/* Prioritise for reclaim when writeback ends */

	NR_DIRTIED,		/* page dirtyings since bootup */

	NR_WRITTEN,		/* page writings since bootup */

	NR_VM_NODE_STAT_ITEMS

};

include/trace/events/writeback.h

+2 −2
Original line number Diff line number Diff line
@@ -415,8 +415,8 @@ TRACE_EVENT(global_dirty_state, 
		__entry->nr_dirty	= global_node_page_state(NR_FILE_DIRTY);

		__entry->nr_writeback	= global_node_page_state(NR_WRITEBACK);

		__entry->nr_unstable	= global_node_page_state(NR_UNSTABLE_NFS);

		__entry->nr_dirtied	= global_page_state(NR_DIRTIED);

		__entry->nr_written	= global_page_state(NR_WRITTEN);

		__entry->nr_dirtied	= global_node_page_state(NR_DIRTIED);

		__entry->nr_written	= global_node_page_state(NR_WRITTEN);

		__entry->background_thresh = background_thresh;

		__entry->dirty_thresh	= dirty_thresh;

		__entry->dirty_limit	= global_wb_domain.dirty_limit;

mm/page-writeback.c

+3 −3
Original line number Diff line number Diff line
@@ -2461,7 +2461,7 @@ 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_zone_page_state(page, NR_DIRTIED);

		__inc_node_page_state(page, NR_DIRTIED);

		__inc_wb_stat(wb, WB_RECLAIMABLE);

		__inc_wb_stat(wb, WB_DIRTIED);

		task_io_account_write(PAGE_SIZE);
@@ -2550,7 +2550,7 @@ void account_page_redirty(struct page *page) 


		wb = unlocked_inode_to_wb_begin(inode, &locked);

		current->nr_dirtied--;

		dec_zone_page_state(page, NR_DIRTIED);

		dec_node_page_state(page, NR_DIRTIED);

		dec_wb_stat(wb, WB_DIRTIED);

		unlocked_inode_to_wb_end(inode, locked);

	}
@@ -2787,7 +2787,7 @@ int test_clear_page_writeback(struct page *page) 
		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_zone_page_state(page, NR_WRITTEN);

		inc_node_page_state(page, NR_WRITTEN);

	}

	unlock_page_memcg(page);

	return ret;

mm/vmscan.c

+2 −2
Original line number Diff line number Diff line
@@ -612,7 +612,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, 
			ClearPageReclaim(page);

		}

		trace_mm_vmscan_writepage(page);

		inc_zone_page_state(page, NR_VMSCAN_WRITE);

		inc_node_page_state(page, NR_VMSCAN_WRITE);

		return PAGE_SUCCESS;

	}
@@ -1117,7 +1117,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, 
				 * except we already have the page isolated

				 * and know it's dirty

				 */

				inc_zone_page_state(page, NR_VMSCAN_IMMEDIATE);

				inc_node_page_state(page, NR_VMSCAN_IMMEDIATE);

				SetPageReclaim(page);



				goto keep_locked;

mm/vmstat.c

+4 −4
Original line number Diff line number Diff line
@@ -931,10 +931,6 @@ const char * const vmstat_text[] = { 
	"nr_page_table_pages",

	"nr_kernel_stack",

	"nr_bounce",

	"nr_vmscan_write",

	"nr_vmscan_immediate_reclaim",

	"nr_dirtied",

	"nr_written",

#if IS_ENABLED(CONFIG_ZSMALLOC)

	"nr_zspages",

#endif
@@ -971,6 +967,10 @@ const char * const vmstat_text[] = { 
	"nr_shmem_pmdmapped",

	"nr_anon_transparent_hugepages",

	"nr_unstable",

	"nr_vmscan_write",

	"nr_vmscan_immediate_reclaim",

	"nr_dirtied",

	"nr_written",



	/* enum writeback_stat_item counters */

	"nr_dirty_threshold",

CRA Git | Maintained and supported by SUSTech CRA and CCSE