mm: vmstat: add isolate pages

If the system is running a heavy load of processes then concurrent reclaim
can isolate a large number of pages from the LRU. /proc/vmstat and the
output generated for an OOM do not show how many pages were isolated.

This has been observed during process fork bomb testing (mstctl11 in LTP).

This patch shows the information about isolated pages.

Reproduced via:

-----------------------
% ./hackbench 140 process 1000
   => OOM occur

active_anon:146 inactive_anon:0 isolated_anon:49245
 active_file:79 inactive_file:18 isolated_file:113
 unevictable:0 dirty:0 writeback:0 unstable:0 buffer:39
 free:370 slab_reclaimable:309 slab_unreclaimable:5492
 mapped:53 shmem:15 pagetables:28140 bounce:0

Signed-off-by: KOSAKI Motohiro <kosaki.motohiro@jp.fujitsu.com>
Acked-by: Rik van Riel <riel@redhat.com>
Acked-by: Wu Fengguang <fengguang.wu@intel.com>
Reviewed-by: Minchan Kim <minchan.kim@gmail.com>
Cc: Hugh Dickins <hugh.dickins@tiscali.co.uk>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index b3583b9..9c50309 100644 (file)
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -100,6 +100,8 @@ enum zone_stat_item {
        NR_BOUNCE,
        NR_VMSCAN_WRITE,
        NR_WRITEBACK_TEMP,      /* Writeback using temporary buffers */
+       NR_ISOLATED_ANON,       /* Temporary isolated pages from anon lru */
+       NR_ISOLATED_FILE,       /* Temporary isolated pages from file lru */
        NR_SHMEM,               /* shmem pages (included tmpfs/GEM pages) */
 #ifdef CONFIG_NUMA
        NUMA_HIT,               /* allocated in intended node */

diff --git a/mm/migrate.c b/mm/migrate.c
index 37143b9..b535a2c 100644 (file)
--- a/mm/migrate.c
+++ b/mm/migrate.c
@@ -67,6 +67,8 @@ int putback_lru_pages(struct list_head *l)
 
        list_for_each_entry_safe(page, page2, l, lru) {
                list_del(&page->lru);
+               dec_zone_page_state(page, NR_ISOLATED_ANON +
+                                   !!page_is_file_cache(page));
                putback_lru_page(page);
                count++;
        }
@@ -698,6 +700,8 @@ unlock:
                 * restored.
                 */
                list_del(&page->lru);
+               dec_zone_page_state(page, NR_ISOLATED_ANON +
+                                   !!page_is_file_cache(page));
                putback_lru_page(page);
        }
 
@@ -742,6 +746,13 @@ int migrate_pages(struct list_head *from,
        struct page *page2;
        int swapwrite = current->flags & PF_SWAPWRITE;
        int rc;
+       unsigned long flags;
+
+       local_irq_save(flags);
+       list_for_each_entry(page, from, lru)
+               __inc_zone_page_state(page, NR_ISOLATED_ANON +
+                                     !!page_is_file_cache(page));
+       local_irq_restore(flags);
 
        if (!swapwrite)
                current->flags |= PF_SWAPWRITE;

diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index b6d0d09..afda8fd 100644 (file)
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2134,16 +2134,18 @@ void show_free_areas(void)
                }
        }
 
-       printk("Active_anon:%lu active_file:%lu inactive_anon:%lu\n"
-               " inactive_file:%lu"
+       printk("active_anon:%lu inactive_anon:%lu isolated_anon:%lu\n"
+               " active_file:%lu inactive_file:%lu isolated_file:%lu\n"
                " unevictable:%lu"
                " dirty:%lu writeback:%lu unstable:%lu buffer:%lu\n"
                " free:%lu slab_reclaimable:%lu slab_unreclaimable:%lu\n"
                " mapped:%lu shmem:%lu pagetables:%lu bounce:%lu\n",
                global_page_state(NR_ACTIVE_ANON),
-               global_page_state(NR_ACTIVE_FILE),
                global_page_state(NR_INACTIVE_ANON),
+               global_page_state(NR_ISOLATED_ANON),
+               global_page_state(NR_ACTIVE_FILE),
                global_page_state(NR_INACTIVE_FILE),
+               global_page_state(NR_ISOLATED_FILE),
                global_page_state(NR_UNEVICTABLE),
                global_page_state(NR_FILE_DIRTY),
                global_page_state(NR_WRITEBACK),
@@ -2171,6 +2173,8 @@ void show_free_areas(void)
                        " active_file:%lukB"
                        " inactive_file:%lukB"
                        " unevictable:%lukB"
+                       " isolated(anon):%lukB"
+                       " isolated(file):%lukB"
                        " present:%lukB"
                        " mlocked:%lukB"
                        " dirty:%lukB"
@@ -2197,6 +2201,8 @@ void show_free_areas(void)
                        K(zone_page_state(zone, NR_ACTIVE_FILE)),
                        K(zone_page_state(zone, NR_INACTIVE_FILE)),
                        K(zone_page_state(zone, NR_UNEVICTABLE)),
+                       K(zone_page_state(zone, NR_ISOLATED_ANON)),
+                       K(zone_page_state(zone, NR_ISOLATED_FILE)),
                        K(zone->present_pages),
                        K(zone_page_state(zone, NR_MLOCK)),
                        K(zone_page_state(zone, NR_FILE_DIRTY)),

diff --git a/mm/vmscan.c b/mm/vmscan.c
index d86a91f..75c2997 100644 (file)
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -1072,6 +1072,8 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
                unsigned long nr_active;
                unsigned int count[NR_LRU_LISTS] = { 0, };
                int mode = lumpy_reclaim ? ISOLATE_BOTH : ISOLATE_INACTIVE;
+               unsigned long nr_anon;
+               unsigned long nr_file;
 
                nr_taken = sc->isolate_pages(sc->swap_cluster_max,
                             &page_list, &nr_scan, sc->order, mode,
@@ -1102,6 +1104,10 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
                __mod_zone_page_state(zone, NR_INACTIVE_ANON,
                                                -count[LRU_INACTIVE_ANON]);
 
+               nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON];
+               nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE];
+               __mod_zone_page_state(zone, NR_ISOLATED_ANON, nr_anon);
+               __mod_zone_page_state(zone, NR_ISOLATED_FILE, nr_file);
 
                reclaim_stat->recent_scanned[0] += count[LRU_INACTIVE_ANON];
                reclaim_stat->recent_scanned[0] += count[LRU_ACTIVE_ANON];
@@ -1169,6 +1175,9 @@ static unsigned long shrink_inactive_list(unsigned long max_scan,
                                spin_lock_irq(&zone->lru_lock);
                        }
                }
+               __mod_zone_page_state(zone, NR_ISOLATED_ANON, -nr_anon);
+               __mod_zone_page_state(zone, NR_ISOLATED_FILE, -nr_file);
+
        } while (nr_scanned < max_scan);
 
 done:
@@ -1279,6 +1288,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
                __mod_zone_page_state(zone, NR_ACTIVE_FILE, -nr_taken);
        else
                __mod_zone_page_state(zone, NR_ACTIVE_ANON, -nr_taken);
+       __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, nr_taken);
        spin_unlock_irq(&zone->lru_lock);
 
        while (!list_empty(&l_hold)) {
@@ -1329,7 +1339,7 @@ static void shrink_active_list(unsigned long nr_pages, struct zone *zone,
                                                LRU_ACTIVE + file * LRU_FILE);
        move_active_pages_to_lru(zone, &l_inactive,
                                                LRU_BASE   + file * LRU_FILE);
-
+       __mod_zone_page_state(zone, NR_ISOLATED_ANON + file, -nr_taken);
        spin_unlock_irq(&zone->lru_lock);
 }
 

diff --git a/mm/vmstat.c b/mm/vmstat.c
index 7214a45..c81321f 100644 (file)
--- a/mm/vmstat.c
+++ b/mm/vmstat.c
@@ -644,6 +644,8 @@ static const char * const vmstat_text[] = {
        "nr_bounce",
        "nr_vmscan_write",
        "nr_writeback_temp",
+       "nr_isolated_anon",
+       "nr_isolated_file",
        "nr_shmem",
 #ifdef CONFIG_NUMA
        "numa_hit",