Patch series "use up highorder free pages before OOM", v3.
I got OOM report from production team with v4.4 kernel. It had enough
free memory but failed to allocate GFP_KERNEL order-0 page and finally
encountered OOM kill. It occured during QA process which launches
several apps, switching and so on. It happned rarely. IOW, In normal
situation, it was not a problem but if we are unluck so that several
apps uses peak memory at the same time, it can happen. If we manage to
pass the phase, the system can go working well.
I could reproduce it with my test(memory spike easily. Look at below.
The reason is free pages(19M) of DMA32 zone are reserved for
HIGHORDERATOMIC and doesn't unreserved before the OOM.
balloon invoked oom-killer: gfp_mask=0x24280ca(GFP_HIGHUSER_MOVABLE|__GFP_ZERO), order=0, oom_score_adj=0
balloon cpuset=/ mems_allowed=0
CPU: 1 PID: 8473 Comm: balloon Tainted: G W OE 4.8.0-rc7-00219-g3f74c9559583-dirty #3161
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
Call Trace:
dump_stack+0x63/0x90
dump_header+0x5c/0x1ce
oom_kill_process+0x22e/0x400
out_of_memory+0x1ac/0x210
__alloc_pages_nodemask+0x101e/0x1040
handle_mm_fault+0xa0a/0xbf0
__do_page_fault+0x1dd/0x4d0
trace_do_page_fault+0x43/0x130
do_async_page_fault+0x1a/0xa0
async_page_fault+0x28/0x30
Mem-Info:
active_anon:383949 inactive_anon:106724 isolated_anon:0
active_file:15 inactive_file:44 isolated_file:0
unevictable:0 dirty:0 writeback:24 unstable:0
slab_reclaimable:2483 slab_unreclaimable:3326
mapped:0 shmem:0 pagetables:1906 bounce:0
free:6898 free_pcp:291 free_cma:0
Node 0 active_anon:1535796kB inactive_anon:426896kB active_file:60kB inactive_file:176kB unevictable:0kB isolated(anon):0kB isolated(file):0kB mapped:0kB dirty:0kB writeback:96kB shmem:0kB writeback_tmp:0kB unstable:0kB pages_scanned:1418 all_unreclaimable? no
DMA free:8188kB min:44kB low:56kB high:68kB active_anon:7648kB inactive_anon:0kB active_file:0kB inactive_file:4kB unevictable:0kB writepending:0kB present:15992kB managed:15908kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:20kB kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB
lowmem_reserve[]: 0 1952 1952 1952
DMA32 free:19404kB min:5628kB low:7624kB high:9620kB active_anon:1528148kB inactive_anon:426896kB active_file:60kB inactive_file:420kB unevictable:0kB writepending:96kB present:2080640kB managed:2030092kB mlocked:0kB slab_reclaimable:9932kB slab_unreclaimable:13284kB kernel_stack:2496kB pagetables:7624kB bounce:0kB free_pcp:900kB local_pcp:112kB free_cma:0kB
lowmem_reserve[]: 0 0 0 0
DMA: 0*4kB 0*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB 0*512kB 0*1024kB 0*2048kB 2*4096kB (H) = 8192kB
DMA32: 7*4kB (H) 8*8kB (H) 30*16kB (H) 31*32kB (H) 14*64kB (H) 9*128kB (H) 2*256kB (H) 2*512kB (H) 4*1024kB (H) 5*2048kB (H) 0*4096kB = 19484kB
51131 total pagecache pages
50795 pages in swap cache
Swap cache stats: add 3532405601, delete 3532354806, find 124289150/1822712228
Free swap = 8kB
Total swap = 255996kB
524158 pages RAM
0 pages HighMem/MovableOnly
12658 pages reserved
0 pages cma reserved
0 pages hwpoisoned
Another example exceeded the limit by the race is
in:imklog: page allocation failure: order:0, mode:0x2280020(GFP_ATOMIC|__GFP_NOTRACK)
CPU: 0 PID: 476 Comm: in:imklog Tainted: G E 4.8.0-rc7-00217-g266ef83c51e5-dirty #3135
Hardware name: QEMU Standard PC (i440FX + PIIX, 1996), BIOS Ubuntu-1.8.2-1ubuntu1 04/01/2014
Call Trace:
dump_stack+0x63/0x90
warn_alloc_failed+0xdb/0x130
__alloc_pages_nodemask+0x4d6/0xdb0
new_slab+0x339/0x490
___slab_alloc.constprop.74+0x367/0x480
__slab_alloc.constprop.73+0x20/0x40
__kmalloc+0x1a4/0x1e0
alloc_indirect.isra.14+0x1d/0x50
virtqueue_add_sgs+0x1c4/0x470
__virtblk_add_req+0xae/0x1f0
virtio_queue_rq+0x12d/0x290
__blk_mq_run_hw_queue+0x239/0x370
blk_mq_run_hw_queue+0x8f/0xb0
blk_mq_insert_requests+0x18c/0x1a0
blk_mq_flush_plug_list+0x125/0x140
blk_flush_plug_list+0xc7/0x220
blk_finish_plug+0x2c/0x40
__do_page_cache_readahead+0x196/0x230
filemap_fault+0x448/0x4f0
ext4_filemap_fault+0x36/0x50
__do_fault+0x75/0x140
handle_mm_fault+0x84d/0xbe0
__do_page_fault+0x1dd/0x4d0
trace_do_page_fault+0x43/0x130
do_async_page_fault+0x1a/0xa0
async_page_fault+0x28/0x30
Mem-Info:
active_anon:363826 inactive_anon:121283 isolated_anon:32
active_file:65 inactive_file:152 isolated_file:0
unevictable:0 dirty:0 writeback:46 unstable:0
slab_reclaimable:2778 slab_unreclaimable:3070
mapped:112 shmem:0 pagetables:1822 bounce:0
free:9469 free_pcp:231 free_cma:0
Node 0 active_anon:1455304kB inactive_anon:485132kB active_file:260kB inactive_file:608kB unevictable:0kB isolated(anon):128kB isolated(file):0kB mapped:448kB dirty:0kB writeback:184kB shmem:0kB writeback_tmp:0kB unstable:0kB pages_scanned:13641 all_unreclaimable? no
DMA free:7748kB min:44kB low:56kB high:68kB active_anon:7944kB inactive_anon:104kB active_file:0kB inactive_file:0kB unevictable:0kB writepending:0kB present:15992kB managed:15908kB mlocked:0kB slab_reclaimable:0kB slab_unreclaimable:108kB kernel_stack:0kB pagetables:4kB bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:0kB
lowmem_reserve[]: 0 1952 1952 1952
DMA32 free:30128kB min:5628kB low:7624kB high:9620kB active_anon:1447360kB inactive_anon:485028kB active_file:260kB inactive_file:608kB unevictable:0kB writepending:184kB present:2080640kB managed:2030132kB mlocked:0kB slab_reclaimable:11112kB slab_unreclaimable:12172kB kernel_stack:2400kB pagetables:7284kB bounce:0kB free_pcp:924kB local_pcp:72kB free_cma:0kB
lowmem_reserve[]: 0 0 0 0
DMA: 7*4kB (UE) 3*8kB (UH) 1*16kB (M) 0*32kB 2*64kB (U) 1*128kB (M) 1*256kB (U) 0*512kB 1*1024kB (U) 1*2048kB (U) 1*4096kB (H) = 7748kB
DMA32: 10*4kB (H) 3*8kB (H) 47*16kB (H) 38*32kB (H) 5*64kB (H) 1*128kB (H) 2*256kB (H) 3*512kB (H) 3*1024kB (H) 3*2048kB (H) 4*4096kB (H) = 30128kB
2775 total pagecache pages
2536 pages in swap cache
Swap cache stats: add 206786828, delete 206784292, find 7323106/106686077
Free swap = 108744kB
Total swap = 255996kB
524158 pages RAM
0 pages HighMem/MovableOnly
12648 pages reserved
0 pages cma reserved
0 pages hwpoisoned
During the investigation, I found some problems with highatomic so this
patch aims to solve the problems and the final goal is to unreserve
every highatomic free pages before the OOM kill.
This patch (of 4):
In page freeing path, migratetype is racy so that a highorderatomic page
could free into non-highorderatomic free list. If that page is
allocated, VM can change the pageblock from higorderatomic to something.
In that case, highatomic pageblock accounting is broken so it doesn't
work(e.g., VM cannot reserve highorderatomic pageblocks any more
although it doesn't reach 1% limit).
So, this patch prohibits the changing from highatomic to other type.
It's no problem because MIGRATE_HIGHATOMIC is not listed in fallback
array so stealing will only happen due to unexpected races which is
really rare. Also, such prohibiting keeps highatomic pageblock more
longer so it would be better for highorderatomic page allocation.
Link: http://lkml.kernel.org/r/1476259429-18279-2-git-send-email-minchan@kernel.org
Signed-off-by: Minchan Kim <minchan@kernel.org>
Acked-by: Vlastimil Babka <vbabka@suse.cz>
Acked-by: Mel Gorman <mgorman@techsingularity.net>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Sangseok Lee <sangseok.lee@lge.com>
Cc: Michal Hocko <mhocko@suse.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We cannot use the pte value used in set_pte_at for pte_same comparison,
because archs like ppc64, filter/add new pte flag in set_pte_at.
Instead fetch the pte value inside hugetlb_cow. We are comparing pte
value to make sure the pte didn't change since we dropped the page table
lock. hugetlb_cow get called with page table lock held, and we can take
a copy of the pte value before we drop the page table lock.
With hugetlbfs, we optimize the MAP_PRIVATE write fault path with no
previous mapping (huge_pte_none entries), by forcing a cow in the fault
path. This avoid take an addition fault to covert a read-only mapping
to read/write. Here we were comparing a recently instantiated pte (via
set_pte_at) to the pte values from linux page table. As explained above
on ppc64 such pte_same check returned wrong result, resulting in us
taking an additional fault on ppc64.
Fixes: 6a119eae94 ("powerpc/mm: Add a _PAGE_PTE bit")
Link: http://lkml.kernel.org/r/20161018154245.18023-1-aneesh.kumar@linux.vnet.ibm.com
Signed-off-by: Aneesh Kumar K.V <aneesh.kumar@linux.vnet.ibm.com>
Reported-by: Jan Stancek <jstancek@redhat.com>
Acked-by: Hillf Danton <hillf.zj@alibaba-inc.com>
Cc: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Scott Wood <scottwood@freescale.com>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Kirill A. Shutemov <kirill.shutemov@linux.intel.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Our system uses significantly more slab memory with memcg enabled with
the latest kernel. With 3.10 kernel, slab uses 2G memory, while with
4.6 kernel, 6G memory is used. The shrinker has problem. Let's see we
have two memcg for one shrinker. In do_shrink_slab:
1. Check cg1. nr_deferred = 0, assume total_scan = 700. batch size
is 1024, then no memory is freed. nr_deferred = 700
2. Check cg2. nr_deferred = 700. Assume freeable = 20, then
total_scan = 10 or 40. Let's assume it's 10. No memory is freed.
nr_deferred = 10.
The deferred share of cg1 is lost in this case. kswapd will free no
memory even run above steps again and again.
The fix makes sure one memcg's deferred share isn't lost.
Link: http://lkml.kernel.org/r/2414be961b5d25892060315fbb56bb19d81d0c07.1476227351.git.shli@fb.com
Signed-off-by: Shaohua Li <shli@fb.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vladimir Davydov <vdavydov@parallels.com>
Cc: <stable@vger.kernel.org> [4.0+]
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
We had some problems with pages getting unmapped in single threaded
affinitized processes. It was tracked down to NUMA scanning.
In this case it doesn't make any sense to unmap pages if the process is
single threaded and the page is already on the node the process is
running on.
Add a check for this case into the numa protection code, and skip
unmapping if true.
In theory the process could be migrated later, but we will eventually
rescan and unmap and migrate then.
In theory this could be made more fancy: remembering this state per
process or even whole mm. However that would need extra tracking and be
more complicated, and the simple check seems to work fine so far.
[ak@linux.intel.com: v3: Minor updates from Mel. Change code layout]
Link: http://lkml.kernel.org/r/1476382117-5440-1-git-send-email-andi@firstfloor.org
Link: http://lkml.kernel.org/r/1476288949-20970-1-git-send-email-andi@firstfloor.org
Signed-off-by: Andi Kleen <ak@linux.intel.com>
Acked-by: Mel Gorman <mgorman@suse.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Reading /proc/slabinfo or monitoring slabtop(1) can become very
expensive if there are many slab caches and if there are very lengthy
per-node partial and/or free lists.
Commit 07a63c41fa ("mm/slab: improve performance of gathering slabinfo
stats") addressed the per-node full lists which showed a significant
improvement when no objects were freed. This patch has the same
motivation and optimizes the remainder of the usecases where there are
very lengthy partial and free lists.
This patch maintains per-node active_slabs (full and partial) and
free_slabs rather than iterating the lists at runtime when reading
/proc/slabinfo.
When allocating 100GB of slab from a test cache where every slab page is
on the partial list, reading /proc/slabinfo (includes all other slab
caches on the system) takes ~247ms on average with 48 samples.
As a result of this patch, the same read takes ~0.856ms on average.
[rientjes@google.com: changelog]
Link: http://lkml.kernel.org/r/alpine.DEB.2.10.1611081505240.13403@chino.kir.corp.google.com
Signed-off-by: Greg Thelen <gthelen@google.com>
Signed-off-by: David Rientjes <rientjes@google.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
The slub allocator gives us some incorrect warnings when
CONFIG_PROFILE_ANNOTATED_BRANCHES is set, as the unlikely() macro
prevents it from seeing that the return code matches what it was before:
mm/slub.c: In function `kmem_cache_free_bulk':
mm/slub.c:262:23: error: `df.s' may be used uninitialized in this function [-Werror=maybe-uninitialized]
mm/slub.c:2943:3: error: `df.cnt' may be used uninitialized in this function [-Werror=maybe-uninitialized]
mm/slub.c:2933:4470: error: `df.freelist' may be used uninitialized in this function [-Werror=maybe-uninitialized]
mm/slub.c:2943:3: error: `df.tail' may be used uninitialized in this function [-Werror=maybe-uninitialized]
I have not been able to come up with a perfect way for dealing with
this, the three options I see are:
- add a bogus initialization, which would increase the runtime overhead
- replace unlikely() with unlikely_notrace()
- remove the unlikely() annotation completely
I checked the object code for a typical x86 configuration and the last
two cases produce the same result, so I went for the last one, which is
the simplest.
Link: http://lkml.kernel.org/r/20161024155704.3114445-1-arnd@arndb.de
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Acked-by: Jesper Dangaard Brouer <brouer@redhat.com>
Cc: Arnd Bergmann <arnd@arndb.de>
Cc: Christoph Lameter <cl@linux.com>
Cc: Pekka Enberg <penberg@kernel.org>
Cc: David Rientjes <rientjes@google.com>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Vladimir Davydov <vdavydov.dev@gmail.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Laura Abbott <labbott@fedoraproject.org>
Cc: Alexander Potapenko <glider@google.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Creating a lot of cgroups at the same time might stall all worker
threads with kmem cache creation works, because kmem cache creation is
done with the slab_mutex held. The problem was amplified by commits
801faf0db8 ("mm/slab: lockless decision to grow cache") in case of
SLAB and 81ae6d0395 ("mm/slub.c: replace kick_all_cpus_sync() with
synchronize_sched() in kmem_cache_shrink()") in case of SLUB, which
increased the maximal time the slab_mutex can be held.
To prevent that from happening, let's use a special ordered single
threaded workqueue for kmem cache creation. This shouldn't introduce
any functional changes regarding how kmem caches are created, as the
work function holds the global slab_mutex during its whole runtime
anyway, making it impossible to run more than one work at a time. By
using a single threaded workqueue, we just avoid creating a thread per
each work. Ordering is required to avoid a situation when a cgroup's
work is put off indefinitely because there are other cgroups to serve,
in other words to guarantee fairness.
Link: https://bugzilla.kernel.org/show_bug.cgi?id=172981
Link: http://lkml.kernel.org/r/20161004131417.GC1862@esperanza
Signed-off-by: Vladimir Davydov <vdavydov.dev@gmail.com>
Reported-by: Doug Smythies <dsmythies@telus.net>
Acked-by: Michal Hocko <mhocko@suse.com>
Cc: Christoph Lameter <cl@linux.com>
Cc: David Rientjes <rientjes@google.com>
Cc: Johannes Weiner <hannes@cmpxchg.org>
Cc: Joonsoo Kim <iamjoonsoo.kim@lge.com>
Cc: Pekka Enberg <penberg@kernel.org>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
struct timespec is not y2038 safe. Use time64_t which is y2038 safe to
represent orphan scan times. time64_t is sufficient here as only the
seconds delta times are relevant.
Also use appropriate time functions that return time in time64_t format.
Time functions now return monotonic time instead of real time as only
delta scan times are relevant and these values are not persistent across
reboots.
The format string for the debug print is still using long as this is
only the time elapsed since the last scan and long is sufficient to
represent this value.
Link: http://lkml.kernel.org/r/1475365138-20567-1-git-send-email-deepa.kernel@gmail.com
Signed-off-by: Deepa Dinamani <deepa.kernel@gmail.com>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Cc: Mark Fasheh <mfasheh@versity.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <jiangqi903@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
In ocfs2_lock_refcount_tree, if ocfs2_read_refcount_block() returns an
error, we do ocfs2_refcount_tree_put twice (once in
ocfs2_unlock_refcount_tree and once outside it), thereby reducing the
refcount of the refcount tree twice, but we dont delete the tree in this
case. This will make refcnt of the tree = 0 and the
ocfs2_refcount_tree_put will eventually call ocfs2_mark_lockres_freeing,
setting OCFS2_LOCK_FREEING for the refcount_tree->rf_lockres.
The error returned by ocfs2_read_refcount_block is propagated all the
way back and for next iteration of write, ocfs2_lock_refcount_tree gets
the same tree back from ocfs2_get_refcount_tree because we havent
deleted the tree. Now we have the same tree, but OCFS2_LOCK_FREEING is
set for rf_lockres and eventually, when _ocfs2_lock_refcount_tree is
called in this iteration, BUG_ON( __ocfs2_cluster_lock:1395 ERROR:
Cluster lock called on freeing lockres T00000000000000000386019775b08d!
flags 0x81) is triggerred.
Call stack:
(loop16,11155,0):ocfs2_lock_refcount_tree:482 ERROR: status = -5
(loop16,11155,0):ocfs2_refcount_cow_hunk:3497 ERROR: status = -5
(loop16,11155,0):ocfs2_refcount_cow:3560 ERROR: status = -5
(loop16,11155,0):ocfs2_prepare_inode_for_refcount:2111 ERROR: status = -5
(loop16,11155,0):ocfs2_prepare_inode_for_write:2190 ERROR: status = -5
(loop16,11155,0):ocfs2_file_write_iter:2331 ERROR: status = -5
(loop16,11155,0):__ocfs2_cluster_lock:1395 ERROR: bug expression:
lockres->l_flags & OCFS2_LOCK_FREEING
(loop16,11155,0):__ocfs2_cluster_lock:1395 ERROR: Cluster lock called on
freeing lockres T00000000000000000386019775b08d! flags 0x81
kernel BUG at fs/ocfs2/dlmglue.c:1395!
invalid opcode: 0000 [#1] SMP CPU 0
Modules linked in: tun ocfs2 jbd2 xen_blkback xen_netback xen_gntdev .. sd_mod crc_t10dif ext3 jbd mbcache
RIP: __ocfs2_cluster_lock+0x31c/0x740 [ocfs2]
RSP: e02b:ffff88017c0138a0 EFLAGS: 00010086
Process loop16 (pid: 11155, threadinfo ffff88017c010000, task ffff8801b5374300)
Call Trace:
ocfs2_refcount_lock+0xae/0x130 [ocfs2]
__ocfs2_lock_refcount_tree+0x29/0xe0 [ocfs2]
ocfs2_lock_refcount_tree+0xdd/0x320 [ocfs2]
ocfs2_refcount_cow_hunk+0x1cb/0x440 [ocfs2]
ocfs2_refcount_cow+0xa9/0x1d0 [ocfs2]
ocfs2_prepare_inode_for_refcount+0x115/0x200 [ocfs2]
ocfs2_prepare_inode_for_write+0x33b/0x470 [ocfs2]
ocfs2_file_write_iter+0x220/0x8c0 [ocfs2]
aio_write_iter+0x2e/0x30
Fix this by avoiding the second call to ocfs2_refcount_tree_put()
Link: http://lkml.kernel.org/r/1473984404-32011-1-git-send-email-ashish.samant@oracle.com
Signed-off-by: Ashish Samant <ashish.samant@oracle.com>
Reviewed-by: Eric Ren <zren@suse.com>
Cc: Mark Fasheh <mfasheh@versity.com>
Cc: Joel Becker <jlbec@evilplan.org>
Cc: Junxiao Bi <junxiao.bi@oracle.com>
Cc: Joseph Qi <jiangqi903@gmail.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Minchan Kim
Andreas Platschek
Aneesh Kumar K.V
Tobias Klauser
Shaohua Li
Andi Kleen
David Rientjes
Greg Thelen
Thomas Garnier
Arnd Bergmann
Vladimir Davydov
Deepa Dinamani
Ashish Samant
piaojun
Guozhonghua
Sudip Mukherjee