Re: [PATCH] fix spurious OOM kills

[Chris Ross <chris@tebibyte.org>]

Andrew Morton escreveu:
> Please ignore the previous patch and try the below.

I still get OOM kills with this (well one, anyway). It does seem harder 
to trigger though.

Regards,
Chris R.


Nov 20 03:24:46 sleepy cpu 0 hot: low 4, high 12, batch 2
Nov 20 03:24:46 sleepy cpu 0 cold: low 0, high 4, batch 2
Nov 20 03:24:46 sleepy HighMem per-cpu: empty
Nov 20 03:24:46 sleepy
Nov 20 03:24:46 sleepy Free pages:        1012kB (0kB HighMem)
Nov 20 03:24:46 sleepy Active:6290 inactive:6215 dirty:0 writeback:0 
unstable:0 free:253 slab:1324 mapped:1 pagetables:56
Nov 20 03:24:46 sleepy DMA free:252kB min:252kB low:312kB high:376kB 
active:5700
kB inactive:5540kB present:16384kB pages_scanned:15950 
all_unreclaimable? yes
Nov 20 03:24:46 sleepy protections[]: 0 0 0
Nov 20 03:24:46 sleepy Normal free:760kB min:764kB low:952kB high:1144kB 
active:19460kB inactive:19320kB present:49144kB pages_scanned:40497 
all_unreclaimabl
e? yes
Nov 20 03:24:46 sleepy protections[]: 0 0 0
Nov 20 03:24:46 sleepy HighMem free:0kB min:128kB low:160kB high:192kB 
active:0kB inactive:0kB present:0kB pages_scanned:0 all_unreclaimable? no
Nov 20 03:24:46 sleepy protections[]: 0 0 0
Nov 20 03:24:46 sleepy DMA: 3*4kB 4*8kB 3*16kB 1*32kB 2*64kB 0*128kB 
0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 252kB
Nov 20 03:24:46 sleepy Normal: 10*4kB 2*8kB 4*16kB 4*32kB 2*64kB 3*128kB 
0*256kB 0*512kB 0*1024kB 0*2048kB 0*4096kB = 760kB
Nov 20 03:24:46 sleepy HighMem: empty
Nov 20 03:24:46 sleepy Swap cache: add 4076265, delete 4076262, find 
482017/1245636, race 1+9
Nov 20 03:24:46 sleepy Out of Memory: Killed process 6841 (sshd).
Nov 20 03:24:46 sleepy sshd: page allocation failure. order:0, mode:0x1d2
Nov 20 03:24:46 sleepy [<c010395b>] dump_stack+0x16/0x18
Nov 20 03:24:46 sleepy [<c0144859>] __alloc_pages+0x2fe/0x31a
Nov 20 03:24:46 sleepy [<c0146f2f>] do_page_cache_readahead+0x101/0x18d
Nov 20 03:24:46 sleepy [<c01407c4>] filemap_nopage+0x163/0x337
Nov 20 03:24:46 sleepy [<c015215d>] do_no_page+0x10f/0x534
Nov 20 03:24:46 sleepy [<c0152799>] handle_mm_fault+0xe2/0x261
Nov 20 03:24:46 sleepy [<c0114030>] do_page_fault+0x216/0x5d2
Nov 20 03:24:46 sleepy [<c01034ef>] error_code+0x2b/0x30
Nov 20 03:24:46 sleepy sshd: page allocation failure. order:0, mode:0xd2
Nov 20 03:24:46 sleepy [<c010395b>] dump_stack+0x16/0x18
Nov 20 03:24:46 sleepy [<c0144859>] __alloc_pages+0x2fe/0x31a
Nov 20 03:24:46 sleepy [<c015a3d6>] read_swap_cache_async+0x33/0xa5
Nov 20 03:24:46 sleepy [<c0151813>] swapin_readahead+0x3c/0x81
Nov 20 03:24:46 sleepy [<c0151920>] do_swap_page+0xc8/0x4c6
Nov 20 03:24:46 sleepy [<c01527c1>] handle_mm_fault+0x10a/0x261
Nov 20 03:24:46 sleepy [<c0114030>] do_page_fault+0x216/0x5d2
Nov 20 03:24:46 sleepy [<c01034ef>] error_code+0x2b/0x30
Nov 20 03:24:46 sleepy sshd: page allocation failure. order:0, mode:0xd2
Nov 20 03:24:46 sleepy [<c010395b>] dump_stack+0x16/0x18
Nov 20 03:24:46 sleepy [<c0144859>] __alloc_pages+0x2fe/0x31a
--
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: <a href=mailto:"aart@kvack.org"> aart@kvack.org </a>