From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932573AbcGHJjQ (ORCPT ); Fri, 8 Jul 2016 05:39:16 -0400 Received: from outbound-smtp03.blacknight.com ([81.17.249.16]:58504 "EHLO outbound-smtp03.blacknight.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932522AbcGHJix (ORCPT ); Fri, 8 Jul 2016 05:38:53 -0400 From: Mel Gorman To: Andrew Morton , Linux-MM Cc: Rik van Riel , Vlastimil Babka , Johannes Weiner , Minchan Kim , Joonsoo Kim , LKML , Mel Gorman Subject: [PATCH 20/34] mm: move vmscan writes and file write accounting to the node Date: Fri, 8 Jul 2016 10:34:56 +0100 Message-Id: <1467970510-21195-21-git-send-email-mgorman@techsingularity.net> X-Mailer: git-send-email 2.6.4 In-Reply-To: <1467970510-21195-1-git-send-email-mgorman@techsingularity.net> References: <1467970510-21195-1-git-send-email-mgorman@techsingularity.net> Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org 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 Acked-by: Vlastimil Babka Acked-by: Michal Hocko --- 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 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-wm0-f72.google.com (mail-wm0-f72.google.com [74.125.82.72]) by kanga.kvack.org (Postfix) with ESMTP id 4E7E96B026D for ; Fri, 8 Jul 2016 05:38:49 -0400 (EDT) Received: by mail-wm0-f72.google.com with SMTP id x83so5281372wma.2 for ; Fri, 08 Jul 2016 02:38:49 -0700 (PDT) Received: from outbound-smtp02.blacknight.com (outbound-smtp02.blacknight.com. [81.17.249.8]) by mx.google.com with ESMTPS id i19si2248419wjq.170.2016.07.08.02.38.46 for (version=TLS1 cipher=AES128-SHA bits=128/128); Fri, 08 Jul 2016 02:38:46 -0700 (PDT) Received: from mail.blacknight.com (pemlinmail01.blacknight.ie [81.17.254.10]) by outbound-smtp02.blacknight.com (Postfix) with ESMTPS id 727DD1DC071 for ; Fri, 8 Jul 2016 09:38:46 +0000 (UTC) From: Mel Gorman Subject: [PATCH 20/34] mm: move vmscan writes and file write accounting to the node Date: Fri, 8 Jul 2016 10:34:56 +0100 Message-Id: <1467970510-21195-21-git-send-email-mgorman@techsingularity.net> In-Reply-To: <1467970510-21195-1-git-send-email-mgorman@techsingularity.net> References: <1467970510-21195-1-git-send-email-mgorman@techsingularity.net> Sender: owner-linux-mm@kvack.org List-ID: To: Andrew Morton , Linux-MM Cc: Rik van Riel , Vlastimil Babka , Johannes Weiner , Minchan Kim , Joonsoo Kim , LKML , Mel Gorman 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 Acked-by: Vlastimil Babka Acked-by: Michal Hocko --- 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 -- To unsubscribe, send a message with 'unsubscribe linux-mm' in the body to majordomo@kvack.org. For more info on Linux MM, see: http://www.linux-mm.org/ . Don't email: email@kvack.org