* ARM: nommu: Unable to allocate RAM for process text/data, errno 12
@ 2013-11-26 9:29 Axel Lin
2013-11-27 0:44 ` Andrew Morton
0 siblings, 1 reply; 3+ messages in thread
From: Axel Lin @ 2013-11-26 9:29 UTC (permalink / raw)
To: linux-kernel, linux-arm-kernel; +Cc: Andrew Morton
Hi,
I got below error messages while starting mdev (busybox).
/ # free
total used free shared buffers
Mem: 23628 8924 14704 0 72
-/+ buffers: 8852 14776
/ # exec /sbin/init
Starting logging: OK
Starting mdev...
[ 108.537109] chmod: page allocation failure: order:8, mode:0xd0
[ 108.543945] CPU: 0 PID: 47 Comm: chmod Not tainted 3.13.0-rc1-00170-g1bab531-dirty #1940
[ 108.580078] [<0000c430>] (unwind_backtrace+0x0/0xe0) from [<0000ae58>] (show_stack+0x10/0x14)
[ 108.592773] [<0000ae58>] (show_stack+0x10/0x14) from [<00050010>] (warn_alloc_failed+0xf8/0x128)
[ 108.605468] [<00050010>] (warn_alloc_failed+0xf8/0x128) from [<00052030>] (__alloc_pages_nodemask+0x64c/0x6c4)
[ 108.620117] [<00052030>] (__alloc_pages_nodemask+0x64c/0x6c4) from [<0005f028>] (do_mmap_pgoff+0x5d0/0x9b0)
[ 108.633789] [<0005f028>] (do_mmap_pgoff+0x5d0/0x9b0) from [<0005ac04>] (vm_mmap_pgoff+0x64/0x7c)
[ 108.647460] [<0005ac04>] (vm_mmap_pgoff+0x64/0x7c) from [<0009e6e8>] (load_flat_binary+0x38c/0xa0c)
[ 108.660156] [<0009e6e8>] (load_flat_binary+0x38c/0xa0c) from [<0006bc40>] (search_binary_handler+0x4c/0xa4)
[ 108.676757] [<0006bc40>] (search_binary_handler+0x4c/0xa4) from [<0006bfc8>] (do_execve+0x330/0x4e8)
[ 108.689453] [<0006bfc8>] (do_execve+0x330/0x4e8) from [<0006c3c4>] (SyS_execve+0x30/0x44)
[ 108.701171] [<0006c3c4>] (SyS_execve+0x30/0x44) from [<00008f40>] (ret_fast_syscall+0x0/0x44)
[ 108.712890] Mem-info:
[ 108.715820] Normal per-cpu:
[ 108.720703] CPU 0: hi: 0, btch: 1 usd: 0
[ 108.730468] active_anon:0 inactive_anon:0 isolated_anon:0
[ 108.730468] active_file:38 inactive_file:69 isolated_file:0
[ 108.730468] unevictable:3 dirty:7 writeback:0 unstable:0
[ 108.730468] free:2897 slab_reclaimable:171 slab_unreclaimable:436
[ 108.730468] mapped:0 shmem:0 pagetables:0 bounce:0
[ 108.730468] free_cma:0
[ 108.767578] Normal free:11588kB min:612kB low:764kB high:916kB active_anon:0kB inactive_anon:0kB active_file:152kB inactive_file:276kB unevictable:o
[ 108.810546] lowmem_reserve[]: 0 0
[ 108.817382] Normal: 41*4kB (UMR) 30*8kB (UMR) 43*16kB (UM) 22*32kB (UEM) 17*64kB (UEM) 12*128kB (UM) 16*256kB (UEMR) 6*512kB (UM) 0*1024kB 0*2048kBB
[ 108.837890] 110 total pagecache pages
[ 108.880859] 8192 pages of RAM
[ 108.884765] 2923 free pages
[ 108.889648] 2285 reserved pages
[ 108.893554] 505 slab pages
[ 108.896484] 24 pages shared
[ 108.902343] 0 pages swap cached
[ 108.906249] Allocation of length 774144 from process 47 (chmod) failed
[ 108.915039] Normal per-cpu:
[ 108.918945] CPU 0: hi: 0, btch: 1 usd: 0
[ 108.927734] active_anon:0 inactive_anon:0 isolated_anon:0
[ 108.927734] active_file:38 inactive_file:69 isolated_file:0
[ 108.927734] unevictable:3 dirty:7 writeback:0 unstable:0
[ 108.927734] free:2897 slab_reclaimable:171 slab_unreclaimable:436
[ 108.927734] mapped:0 shmem:0 pagetables:0 bounce:0
[ 108.927734] free_cma:0
[ 108.964843] Normal free:11588kB min:612kB low:764kB high:916kB active_anon:0kB inactive_anon:0kB active_file:152kB inactive_file:276kB unevictable:o
[ 109.007812] lowmem_reserve[]: 0 0
[ 109.012695] Normal: 41*4kB (UMR) 30*8kB (UMR) 43*16kB (UM) 22*32kB (UEM) 17*64kB (UEM) 12*128kB (UM) 16*256kB (UEMR) 6*512kB (UM) 0*1024kB 0*2048kBB
[ 109.034179] 110 total pagecache pages
[ 109.041015] Unable to allocate RAM for process text/data, errno 12
ILL
[ 116.480468] chmod: page allocation failure: order:8, mode:0xd0
[ 116.490234] CPU: 0 PID: 49 Comm: chmod Not tainted 3.13.0-rc1-00170-g1bab531-dirty #1940
[ 116.502929] [<0000c430>] (unwind_backtrace+0x0/0xe0) from [<0000ae58>] (show_stack+0x10/0x14)
[ 116.515624] [<0000ae58>] (show_stack+0x10/0x14) from [<00050010>] (warn_alloc_failed+0xf8/0x128)
[ 116.530273] [<00050010>] (warn_alloc_failed+0xf8/0x128) from [<00052030>] (__alloc_pages_nodemask+0x64c/0x6c4)
[ 116.543945] [<00052030>] (__alloc_pages_nodemask+0x64c/0x6c4) from [<0005f028>] (do_mmap_pgoff+0x5d0/0x9b0)
[ 116.558593] [<0005f028>] (do_mmap_pgoff+0x5d0/0x9b0) from [<0005ac04>] (vm_mmap_pgoff+0x64/0x7c)
[ 116.572265] [<0005ac04>] (vm_mmap_pgoff+0x64/0x7c) from [<0009e6e8>] (load_flat_binary+0x38c/0xa0c)
[ 116.585937] [<0009e6e8>] (load_flat_binary+0x38c/0xa0c) from [<0006bc40>] (search_binary_handler+0x4c/0xa4)
[ 116.599609] [<0006bc40>] (search_binary_handler+0x4c/0xa4) from [<0006bfc8>] (do_execve+0x330/0x4e8)
[ 116.614257] [<0006bfc8>] (do_execve+0x330/0x4e8) from [<0006c3c4>] (SyS_execve+0x30/0x44)
[ 116.625976] [<0006c3c4>] (SyS_execve+0x30/0x44) from [<00008f40>] (ret_fast_syscall+0x0/0x44)
[ 116.637695] Mem-info:
[ 116.639648] Normal per-cpu:
[ 116.643554] CPU 0: hi: 0, btch: 1 usd: 0
[ 116.652343] active_anon:0 inactive_anon:0 isolated_anon:0
[ 116.652343] active_file:36 inactive_file:57 isolated_file:0
[ 116.652343] unevictable:3 dirty:7 writeback:0 unstable:0
[ 116.652343] free:2872 slab_reclaimable:204 slab_unreclaimable:437
[ 116.652343] mapped:0 shmem:0 pagetables:0 bounce:0
[ 116.652343] free_cma:0
[ 116.691406] Normal free:11488kB min:612kB low:764kB high:916kB active_anon:0kB inactive_anon:0kB active_file:144kB inactive_file:228kB unevictable:o
[ 116.734374] lowmem_reserve[]: 0 0
[ 116.738281] Normal: 38*4kB (UEMR) 35*8kB (UEMR) 47*16kB (UEM) 22*32kB (UM) 16*64kB (UEM) 13*128kB (UEM) 15*256kB (UEMR) 6*512kB (UM) 0*1024kB 0*204B
[ 116.759765] 96 total pagecache pages
[ 116.801757] 8192 pages of RAM
[ 116.807617] 2898 free pages
[ 116.810546] 2285 reserved pages
[ 116.814453] 539 slab pages
[ 116.819335] 22 pages shared
[ 116.822265] 0 pages swap cached
[ 116.828124] Allocation of length 774144 from process 49 (chmod) failed
[ 116.834960] Normal per-cpu:
[ 116.840820] CPU 0: hi: 0, btch: 1 usd: 0
[ 116.847656] active_anon:0 inactive_anon:0 isolated_anon:0
[ 116.847656] active_file:36 inactive_file:57 isolated_file:0
[ 116.847656] unevictable:3 dirty:7 writeback:0 unstable:0
[ 116.847656] free:2872 slab_reclaimable:204 slab_unreclaimable:437
[ 116.847656] mapped:0 shmem:0 pagetables:0 bounce:0
[ 116.847656] free_cma:0
[ 116.884765] Normal free:11488kB min:612kB low:764kB high:916kB active_anon:0kB inactive_anon:0kB active_file:144kB inactive_file:228kB unevictable:o
[ 116.927734] lowmem_reserve[]: 0 0
[ 116.932617] Normal: 38*4kB (UEMR) 35*8kB (UEMR) 47*16kB (UEM) 22*32kB (UM) 16*64kB (UEM) 13*128kB (UEM) 15*256kB (UEMR) 6*512kB (UM) 0*1024kB 0*204B
[ 116.953124] 96 total pagecache pages
[ 116.959960] Unable to allocate RAM for process text/data, errno 12
ILL
Why it got page allocation failure?
Does that mean it run into OOM?
Seem the system still has enough memory available.
Regards,
Axel
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: ARM: nommu: Unable to allocate RAM for process text/data, errno 12
2013-11-26 9:29 ARM: nommu: Unable to allocate RAM for process text/data, errno 12 Axel Lin
@ 2013-11-27 0:44 ` Andrew Morton
2013-11-28 7:29 ` Axel Lin
0 siblings, 1 reply; 3+ messages in thread
From: Andrew Morton @ 2013-11-27 0:44 UTC (permalink / raw)
To: Axel Lin; +Cc: linux-kernel, linux-arm-kernel, Mel Gorman
On Tue, 26 Nov 2013 17:29:29 +0800 Axel Lin <axel.lin@ingics.com> wrote:
> Hi,
> I got below error messages while starting mdev (busybox).
>
> ...
>
> [ 108.537109] chmod: page allocation failure: order:8, mode:0xd0
It wants to allocate 2^8 physically contiguous pages!
> [ 108.543945] CPU: 0 PID: 47 Comm: chmod Not tainted 3.13.0-rc1-00170-g1bab531-dirty #1940
> [ 108.580078] [<0000c430>] (unwind_backtrace+0x0/0xe0) from [<0000ae58>] (show_stack+0x10/0x14)
> [ 108.592773] [<0000ae58>] (show_stack+0x10/0x14) from [<00050010>] (warn_alloc_failed+0xf8/0x128)
> [ 108.605468] [<00050010>] (warn_alloc_failed+0xf8/0x128) from [<00052030>] (__alloc_pages_nodemask+0x64c/0x6c4)
> [ 108.620117] [<00052030>] (__alloc_pages_nodemask+0x64c/0x6c4) from [<0005f028>] (do_mmap_pgoff+0x5d0/0x9b0)
> [ 108.633789] [<0005f028>] (do_mmap_pgoff+0x5d0/0x9b0) from [<0005ac04>] (vm_mmap_pgoff+0x64/0x7c)
> [ 108.647460] [<0005ac04>] (vm_mmap_pgoff+0x64/0x7c) from [<0009e6e8>] (load_flat_binary+0x38c/0xa0c)
> [ 108.660156] [<0009e6e8>] (load_flat_binary+0x38c/0xa0c) from [<0006bc40>] (search_binary_handler+0x4c/0xa4)
> [ 108.676757] [<0006bc40>] (search_binary_handler+0x4c/0xa4) from [<0006bfc8>] (do_execve+0x330/0x4e8)
> [ 108.689453] [<0006bfc8>] (do_execve+0x330/0x4e8) from [<0006c3c4>] (SyS_execve+0x30/0x44)
> [ 108.701171] [<0006c3c4>] (SyS_execve+0x30/0x44) from [<00008f40>] (ret_fast_syscall+0x0/0x44)
So the binfmt_flat driver is allocating memory into which to load
mdev's text (I assume it's the text).
> Why it got page allocation failure?
Because 256 physically contiguous free pages were not available.
> Does that mean it run into OOM?
Nope.
> Seem the system still has enough memory available.
Sure, but it is too fragmented. Get an MMU ;)
otoh, memory reclaim *should* have at least reclaimed non-mmapped
pagecache. Shooting down lots of pagecache is preferable to failing
exec(). But I expect the PAGE_ALLOC_COSTLY_ORDER logic prevents the kernel
from trying to do this.
If it's repeatable then something like this:
--- a/mm/nommu.c~a
+++ a/mm/nommu.c
@@ -1173,7 +1173,7 @@ static int do_mmap_private(struct vm_are
order = get_order(len);
kdebug("alloc order %d for %lx", order, len);
- pages = alloc_pages(GFP_KERNEL, order);
+ pages = alloc_pages(GFP_KERNEL|__GFP_REPEAT, order);
if (!pages)
goto enomem;
*might* help.
^ permalink raw reply [flat|nested] 3+ messages in thread
* Re: ARM: nommu: Unable to allocate RAM for process text/data, errno 12
2013-11-27 0:44 ` Andrew Morton
@ 2013-11-28 7:29 ` Axel Lin
0 siblings, 0 replies; 3+ messages in thread
From: Axel Lin @ 2013-11-28 7:29 UTC (permalink / raw)
To: Andrew Morton; +Cc: linux-kernel, linux-arm-kernel, Mel Gorman
2013/11/27 Andrew Morton <akpm@linux-foundation.org>:
> On Tue, 26 Nov 2013 17:29:29 +0800 Axel Lin <axel.lin@ingics.com> wrote:
>
>> Hi,
>> I got below error messages while starting mdev (busybox).
>>
>> ...
>>
>> [ 108.537109] chmod: page allocation failure: order:8, mode:0xd0
>
> It wants to allocate 2^8 physically contiguous pages!
>
>> [ 108.543945] CPU: 0 PID: 47 Comm: chmod Not tainted 3.13.0-rc1-00170-g1bab531-dirty #1940
>> [ 108.580078] [<0000c430>] (unwind_backtrace+0x0/0xe0) from [<0000ae58>] (show_stack+0x10/0x14)
>> [ 108.592773] [<0000ae58>] (show_stack+0x10/0x14) from [<00050010>] (warn_alloc_failed+0xf8/0x128)
>> [ 108.605468] [<00050010>] (warn_alloc_failed+0xf8/0x128) from [<00052030>] (__alloc_pages_nodemask+0x64c/0x6c4)
>> [ 108.620117] [<00052030>] (__alloc_pages_nodemask+0x64c/0x6c4) from [<0005f028>] (do_mmap_pgoff+0x5d0/0x9b0)
>> [ 108.633789] [<0005f028>] (do_mmap_pgoff+0x5d0/0x9b0) from [<0005ac04>] (vm_mmap_pgoff+0x64/0x7c)
>> [ 108.647460] [<0005ac04>] (vm_mmap_pgoff+0x64/0x7c) from [<0009e6e8>] (load_flat_binary+0x38c/0xa0c)
>> [ 108.660156] [<0009e6e8>] (load_flat_binary+0x38c/0xa0c) from [<0006bc40>] (search_binary_handler+0x4c/0xa4)
>> [ 108.676757] [<0006bc40>] (search_binary_handler+0x4c/0xa4) from [<0006bfc8>] (do_execve+0x330/0x4e8)
>> [ 108.689453] [<0006bfc8>] (do_execve+0x330/0x4e8) from [<0006c3c4>] (SyS_execve+0x30/0x44)
>> [ 108.701171] [<0006c3c4>] (SyS_execve+0x30/0x44) from [<00008f40>] (ret_fast_syscall+0x0/0x44)
>
> So the binfmt_flat driver is allocating memory into which to load
> mdev's text (I assume it's the text).
>
>> Why it got page allocation failure?
>
> Because 256 physically contiguous free pages were not available.
>
>> Does that mean it run into OOM?
>
> Nope.
>
>> Seem the system still has enough memory available.
>
> Sure, but it is too fragmented. Get an MMU ;)
>
>
> otoh, memory reclaim *should* have at least reclaimed non-mmapped
> pagecache. Shooting down lots of pagecache is preferable to failing
> exec(). But I expect the PAGE_ALLOC_COSTLY_ORDER logic prevents the kernel
> from trying to do this.
>
> If it's repeatable then something like this:
>
> --- a/mm/nommu.c~a
> +++ a/mm/nommu.c
> @@ -1173,7 +1173,7 @@ static int do_mmap_private(struct vm_are
> order = get_order(len);
> kdebug("alloc order %d for %lx", order, len);
>
> - pages = alloc_pages(GFP_KERNEL, order);
> + pages = alloc_pages(GFP_KERNEL|__GFP_REPEAT, order);
> if (!pages)
> goto enomem;
>
>
> *might* help.
Hi Andrew,
Thanks for your reply.
I try to boot a couple times with your patch.
Sometimes I can still see the same (above) messages with your patch applied.
I'm trying to remove unnecessary features to reduce memory usage.
(seems this does help. I got more free memory so less chance to hit
memory allocation failure)
Is it possible to know current memory consumption (slab) in a running system?
BTW, I'm wondering what is the guidline to choose the SLAB allocator?
(especially, for embedded platforms without mmu).
I google for slab/slub/slob, and found some material [1] says:
SLOB (Simple List Of Blocks) is a memory allocator optimized for
embedded systems
with very little memory—on the order of megabytes.
But it also says SLOB suffer from pathological fragmentation.
So I'm wondering if I should choose SLOB or not. ( Currently, I'm using SLUB ).
[1] http://stackoverflow.com/questions/15470560/what-to-choose-between-slab-and-slub-allocator-in-linux-kernel
Regards,
Axel
^ permalink raw reply [flat|nested] 3+ messages in thread
end of thread, other threads:[~2013-11-28 7:29 UTC | newest]
Thread overview: 3+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2013-11-26 9:29 ARM: nommu: Unable to allocate RAM for process text/data, errno 12 Axel Lin
2013-11-27 0:44 ` Andrew Morton
2013-11-28 7:29 ` Axel Lin
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).