Commit 71c799f4 authored by Minchan Kim's avatar Minchan Kim Committed by Linus Torvalds

mm: add per-zone lru list stat

When I did stress test with hackbench, I got OOM message frequently
which didn't ever happen in zone-lru.

  gfp_mask=0x26004c0(GFP_KERNEL|__GFP_REPEAT|__GFP_NOTRACK), order=0
  ..
  ..
   __alloc_pages_nodemask+0xe52/0xe60
   ? new_slab+0x39c/0x3b0
   new_slab+0x39c/0x3b0
   ___slab_alloc.constprop.87+0x6da/0x840
   ? __alloc_skb+0x3c/0x260
   ? _raw_spin_unlock_irq+0x27/0x60
   ? trace_hardirqs_on_caller+0xec/0x1b0
   ? finish_task_switch+0xa6/0x220
   ? poll_select_copy_remaining+0x140/0x140
   __slab_alloc.isra.81.constprop.86+0x40/0x6d
   ? __alloc_skb+0x3c/0x260
   kmem_cache_alloc+0x22c/0x260
   ? __alloc_skb+0x3c/0x260
   __alloc_skb+0x3c/0x260
   alloc_skb_with_frags+0x4e/0x1a0
   sock_alloc_send_pskb+0x16a/0x1b0
   ? wait_for_unix_gc+0x31/0x90
   ? alloc_set_pte+0x2ad/0x310
   unix_stream_sendmsg+0x28d/0x340
   sock_sendmsg+0x2d/0x40
   sock_write_iter+0x6c/0xc0
   __vfs_write+0xc0/0x120
   vfs_write+0x9b/0x1a0
   ? __might_fault+0x49/0xa0
   SyS_write+0x44/0x90
   do_fast_syscall_32+0xa6/0x1e0
   sysenter_past_esp+0x45/0x74

  Mem-Info:
  active_anon:104698 inactive_anon:105791 isolated_anon:192
   active_file:433 inactive_file:283 isolated_file:22
   unevictable:0 dirty:0 writeback:296 unstable:0
   slab_reclaimable:6389 slab_unreclaimable:78927
   mapped:474 shmem:0 pagetables:101426 bounce:0
   free:10518 free_pcp:334 free_cma:0
  Node 0 active_anon:418792kB inactive_anon:423164kB active_file:1732kB inactive_file:1132kB unevictable:0kB isolated(anon):768kB isolated(file):88kB mapped:1896kB dirty:0kB writeback:1184kB shmem:0kB writeback_tmp:0kB unstable:0kB pages_scanned:1478632 all_unreclaimable? yes
  DMA free:3304kB min:68kB low:84kB high:100kB present:15992kB managed:15916kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:4088kB kernel_stack:0kB pagetables:2480kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB
  lowmem_reserve[]: 0 809 1965 1965
  Normal free:3436kB min:3604kB low:4504kB high:5404kB present:897016kB managed:858460kB mlocked:0kB slab_reclaimable:25556kB slab_unreclaimable:311712kB kernel_stack:164608kB pagetables:30844kB bounce:0kB free_pcp:620kB local_pcp:104kB free_cma:0kB
  lowmem_reserve[]: 0 0 9247 9247
  HighMem free:33808kB min:512kB low:1796kB high:3080kB present:1183736kB managed:1183736kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:372252kB bounce:0kB free_pcp:428kB local_pcp:72kB free_cma:0kB
  lowmem_reserve[]: 0 0 0 0
  DMA: 2*4kB (UM) 2*8kB (UM) 0*16kB 1*32kB (U) 1*64kB (U) 2*128kB (UM) 1*256kB (U) 1*512kB (M) 0*1024kB 1*2048kB (U) 0*4096kB = 3192kB
  Normal: 33*4kB (MH) 79*8kB (ME) 11*16kB (M) 4*32kB (M) 2*64kB (ME) 2*128kB (EH) 7*256kB (EH) 0*512kB 0*1024kB 0*2048kB 0*4096kB = 3244kB
  HighMem: 2590*4kB (UM) 1568*8kB (UM) 491*16kB (UM) 60*32kB (UM) 6*64kB (M) 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 33064kB
  Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=2048kB
  25121 total pagecache pages
  24160 pages in swap cache
  Swap cache stats: add 86371, delete 62211, find 42865/60187
  Free swap  = 4015560kB
  Total swap = 4192252kB
  524186 pages RAM
  295934 pages HighMem/MovableOnly
  9658 pages reserved
  0 pages cma reserved

The order-0 allocation for normal zone failed while there are a lot of
reclaimable memory(i.e., anonymous memory with free swap).  I wanted to
analyze the problem but it was hard because we removed per-zone lru stat
so I couldn't know how many of anonymous memory there are in normal/dma
zone.

When we investigate OOM problem, reclaimable memory count is crucial
stat to find a problem.  Without it, it's hard to parse the OOM message
so I believe we should keep it.

With per-zone lru stat,

  gfp_mask=0x26004c0(GFP_KERNEL|__GFP_REPEAT|__GFP_NOTRACK), order=0
  Mem-Info:
  active_anon:101103 inactive_anon:102219 isolated_anon:0
   active_file:503 inactive_file:544 isolated_file:0
   unevictable:0 dirty:0 writeback:34 unstable:0
   slab_reclaimable:6298 slab_unreclaimable:74669
   mapped:863 shmem:0 pagetables:100998 bounce:0
   free:23573 free_pcp:1861 free_cma:0
  Node 0 active_anon:404412kB inactive_anon:409040kB active_file:2012kB inactive_file:2176kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:3452kB dirty:0kB writeback:136kB shmem:0kB writeback_tmp:0kB unstable:0kB pages_scanned:1320845 all_unreclaimable? yes
  DMA free:3296kB min:68kB low:84kB high:100kB active_anon:5540kB inactive_anon:0kB active_file:0kB inactive_file:0kB present:15992kB managed:15916kB mlocked:0kB slab_reclaimable:248kB slab_unreclaimable:2628kB kernel_stack:792kB pagetables:2316kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB
  lowmem_reserve[]: 0 809 1965 1965
  Normal free:3600kB min:3604kB low:4504kB high:5404kB active_anon:86304kB inactive_anon:0kB active_file:160kB inactive_file:376kB present:897016kB managed:858524kB mlocked:0kB slab_reclaimable:24944kB slab_unreclaimable:296048kB kernel_stack:163832kB pagetables:35892kB bounce:0kB free_pcp:3076kB local_pcp:656kB free_cma:0kB
  lowmem_reserve[]: 0 0 9247 9247
  HighMem free:86156kB min:512kB low:1796kB high:3080kB active_anon:312852kB inactive_anon:410024kB active_file:1924kB inactive_file:2012kB present:1183736kB managed:1183736kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:0kB kernel_stack:0kB pagetables:365784kB bounce:0kB free_pcp:3868kB local_pcp:720kB free_cma:0kB
  lowmem_reserve[]: 0 0 0 0
  DMA: 8*4kB (UM) 8*8kB (UM) 4*16kB (M) 2*32kB (UM) 2*64kB (UM) 1*128kB (M) 3*256kB (UME) 2*512kB (UE) 1*1024kB (E) 0*2048kB 0*4096kB = 3296kB
  Normal: 240*4kB (UME) 160*8kB (UME) 23*16kB (ME) 3*32kB (UE) 3*64kB (UME) 2*128kB (ME) 1*256kB (U) 0*512kB 0*1024kB 0*2048kB 0*4096kB = 3408kB
  HighMem: 10942*4kB (UM) 3102*8kB (UM) 866*16kB (UM) 76*32kB (UM) 11*64kB (UM) 4*128kB (UM) 1*256kB (M) 0*512kB 0*1024kB 0*2048kB 0*4096kB = 86344kB
  Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 hugepages_size=2048kB
  54409 total pagecache pages
  53215 pages in swap cache
  Swap cache stats: add 300982, delete 247765, find 157978/226539
  Free swap  = 3803244kB
  Total swap = 4192252kB
  524186 pages RAM
  295934 pages HighMem/MovableOnly
  9642 pages reserved
  0 pages cma reserved

With that, we can see normal zone has a 86M reclaimable memory so we can
know something goes wrong(I will fix the problem in next patch) in
reclaim.

[mgorman@techsingularity.net: rename zone LRU stats in /proc/vmstat]
 Link: http://lkml.kernel.org/r/20160725072300.GK10438@techsingularity.net
Link: http://lkml.kernel.org/r/1469110261-7365-2-git-send-email-mgorman@techsingularity.netSigned-off-by: default avatarMinchan Kim <minchan@kernel.org>
Signed-off-by: default avatarMel Gorman <mgorman@techsingularity.net>
Acked-by: default avatarJohannes Weiner <hannes@cmpxchg.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 785b99fe
......@@ -45,6 +45,8 @@ static __always_inline void __update_lru_size(struct lruvec *lruvec,
struct pglist_data *pgdat = lruvec_pgdat(lruvec);
__mod_node_page_state(pgdat, NR_LRU_BASE + lru, nr_pages);
__mod_zone_page_state(&pgdat->node_zones[zid],
NR_ZONE_LRU_BASE + lru, nr_pages);
acct_highmem_file_pages(zid, lru, nr_pages);
}
......
......@@ -110,6 +110,12 @@ struct zone_padding {
enum zone_stat_item {
/* First 128 byte cacheline (assuming 64 bit words) */
NR_FREE_PAGES,
NR_ZONE_LRU_BASE, /* Used only for compaction and reclaim retry */
NR_ZONE_INACTIVE_ANON = NR_ZONE_LRU_BASE,
NR_ZONE_ACTIVE_ANON,
NR_ZONE_INACTIVE_FILE,
NR_ZONE_ACTIVE_FILE,
NR_ZONE_UNEVICTABLE,
NR_MLOCK, /* mlock()ed pages found and moved off LRU */
NR_SLAB_RECLAIMABLE,
NR_SLAB_UNRECLAIMABLE,
......
......@@ -4356,6 +4356,11 @@ void show_free_areas(unsigned int filter)
" min:%lukB"
" low:%lukB"
" high:%lukB"
" active_anon:%lukB"
" inactive_anon:%lukB"
" active_file:%lukB"
" inactive_file:%lukB"
" unevictable:%lukB"
" present:%lukB"
" managed:%lukB"
" mlocked:%lukB"
......@@ -4373,6 +4378,11 @@ void show_free_areas(unsigned int filter)
K(min_wmark_pages(zone)),
K(low_wmark_pages(zone)),
K(high_wmark_pages(zone)),
K(zone_page_state(zone, NR_ZONE_ACTIVE_ANON)),
K(zone_page_state(zone, NR_ZONE_INACTIVE_ANON)),
K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)),
K(zone_page_state(zone, NR_ZONE_INACTIVE_FILE)),
K(zone_page_state(zone, NR_ZONE_UNEVICTABLE)),
K(zone->present_pages),
K(zone->managed_pages),
K(zone_page_state(zone, NR_MLOCK)),
......
......@@ -1359,23 +1359,14 @@ static __always_inline void update_lru_sizes(struct lruvec *lruvec,
enum lru_list lru, unsigned long *nr_zone_taken,
unsigned long nr_taken)
{
#ifdef CONFIG_HIGHMEM
int zid;
/*
* Highmem has separate accounting for highmem pages so each zone
* is updated separately.
*/
for (zid = 0; zid < MAX_NR_ZONES; zid++) {
if (!nr_zone_taken[zid])
continue;
__update_lru_size(lruvec, lru, zid, -nr_zone_taken[zid]);
}
#else
/* Zone ID does not matter on !HIGHMEM */
__update_lru_size(lruvec, lru, 0, -nr_taken);
#endif
#ifdef CONFIG_MEMCG
mem_cgroup_update_lru_size(lruvec, lru, -nr_taken);
......
......@@ -921,6 +921,11 @@ int fragmentation_index(struct zone *zone, unsigned int order)
const char * const vmstat_text[] = {
/* enum zone_stat_item countes */
"nr_free_pages",
"nr_zone_inactive_anon",
"nr_zone_active_anon",
"nr_zone_inactive_file",
"nr_zone_active_file",
"nr_zone_unevictable",
"nr_mlock",
"nr_slab_reclaimable",
"nr_slab_unreclaimable",
......
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment