Groups | Search | Server Info | Keyboard shortcuts | Login | Register [http] [https] [nntp] [nntps]

Groups > linux.kernel > #1439232

[PATCH 20/34] mm: move vmscan writes and file write accounting to the node

From Mel Gorman <mgorman@techsingularity.net>
Newsgroups linux.kernel
Subject [PATCH 20/34] mm: move vmscan writes and file write accounting to the node
Date 2016-07-08 11:40 +0200
Message-ID <rSAqn-2Tv-49@gated-at.bofh.it> (permalink)
References <rSAqm-2Tv-3@gated-at.bofh.it>
Organization linux.* mail to news gateway

Show all headers | View raw

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.

Signed-off-by: Mel Gorman <mgorman@techsingularity.net>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Michal Hocko <mhocko@suse.com>
---
 include/linux/mmzone.h           | 8 ++++----
 include/trace/events/writeback.h | 4 ++--
 mm/page-writeback.c              | 6 +++---
 mm/vmscan.c                      | 4 ++--
 mm/vmstat.c                      | 8 ++++----
 5 files changed, 15 insertions(+), 15 deletions(-)

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index acd4665c3025..e3d6d42722a0 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -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
 };
 
diff --git a/include/trace/events/writeback.h b/include/trace/events/writeback.h
index ad20f2d2b1f9..2ccd9ccbf9ef 100644
--- a/include/trace/events/writeback.h
+++ b/include/trace/events/writeback.h
@@ -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;
diff --git a/mm/page-writeback.c b/mm/page-writeback.c
index f97591d9fa00..3c02aa603f5a 100644
--- a/mm/page-writeback.c
+++ b/mm/page-writeback.c
@@ -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;
diff --git a/mm/vmscan.c b/mm/vmscan.c
index aef2a6245657..5ad670881d8d 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -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;
diff --git a/mm/vmstat.c b/mm/vmstat.c
index 455392158062..bc94968400d0 100644
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -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",
-- 
2.6.4

Back to linux.kernel | Previous | Next — Previous in thread | Next in thread | Find similar | Unroll thread

Thread

[PATCH 00/34] Move LRU page reclaim from zones to nodes v9 Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 09/34] mm, vmscan: simplify the logic deciding whether kswapd sleeps Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 01/34] mm, vmstat: add infrastructure for per-node vmstats Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 13/34] mm, vmscan: make shrink_node decisions more node-centric Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 16/34] mm, page_alloc: consider dirtyable memory in terms of nodes Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 20/34] mm: move vmscan writes and file write accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 12/34] mm: vmscan: do not reclaim from kswapd if there is any eligible zone Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 24/34] mm, vmscan: avoid passing in classzone_idx unnecessarily to shrink_node Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 14/34] mm, memcg: move memcg limit enforcement from zones to nodes Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 04/34] mm, mmzone: clarify the usage of zone padding Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 02/34] mm, vmscan: move lru_lock to the node Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 15/34] mm, workingset: make working set detection node-aware Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 23/34] mm: convert zone_reclaim to node_reclaim Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:40 +0200
  [PATCH 07/34] mm, vmscan: make kswapd reclaim in terms of nodes Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 30/34] mm: page_alloc: cache the last node whose dirty limit is reached Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 31/34] mm: vmstat: replace __count_zone_vm_events with a zone id equivalent Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 34/34] mm, vmstat: remove zone and node double accounting by approximating retries Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 10/34] mm, vmscan: by default have direct reclaim only shrink once per node Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 32/34] mm: vmstat: account per-zone stalls and pages skipped during reclaim Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 25/34] mm, vmscan: avoid passing in classzone_idx unnecessarily to compaction_ready Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 28/34] mm, vmscan: add classzone information to tracepoints Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 27/34] mm, vmscan: Have kswapd reclaim from all zones if reclaiming and buffer_heads_over_limit Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 26/34] mm, vmscan: avoid passing in remaining unnecessarily to prepare_kswapd_sleep Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 29/34] mm, page_alloc: remove fair zone allocation policy Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 22/34] mm, page_alloc: wake kswapd based on the highest eligible zone Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 33/34] mm, vmstat: print node-based stats in zoneinfo file Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200
  [PATCH 19/34] mm: move most file-based accounting to the node Mel Gorman <mgorman@techsingularity.net> - 2016-07-08 11:50 +0200

csiph-web