My bad, I forgot I don't dynamically allocate the stack trace space so my patch did nothing, I blame the children for distracting me. I've dropped allocating the action altogether for the on disk stuff, that should dramatically reduce the memory usage. You can just do a git pull since I made a new commit. You are mounting with -o ref_verify on only the one fs right? Give this a try and if it still doesn't work we can try a stripped down version that doesn't build the initial tree and just hope that the problem exists in allocating a new block and not modifying the refs for an existing block. Thanks,
Josef Sent from my iPhone > On Sep 2, 2017, at 7:54 PM, Marc MERLIN <m...@merlins.org> wrote: > >> On Sat, Sep 02, 2017 at 04:52:20PM +0000, Josef Bacik wrote: >> Oops, ok I've updated my tree so we don't save the stack trace of the >> initial scan, which we don't need anyway. That should save a decent amount >> of memory in your case. It was an in place update so you'll need to blow >> away your local branch and pull the new one to get the new code. Thanks, > > Still did not work unfortunately (on top of extra unrelated bugs in > 4.13rc5 like I was afraid) > > mounting the partition still sucks all the memory > > [ 358.719722] bcache_writebac invoked oom-killer: > gfp_mask=0x14000c0(GFP_KERNEL), nodemask=(null), order=0, oom_score_adj=0 > [ 358.753716] bcache_writebac cpuset=/ mems_allowed=0 > [ 358.769071] CPU: 3 PID: 2339 Comm: bcache_writebac Tainted: G U > 4.13.0-rc5-amd64-stkreg-sysrq-20170902+ #2 > [ 358.802040] Hardware name: System manufacturer System Product Name/P8H67-M > PRO, BIOS 3904 04/27/2013 > [ 358.830082] Call Trace: > [ 358.838108] dump_stack+0x61/0x7d > [ 358.848728] dump_header+0x97/0x239 > [ 358.859846] ? _raw_spin_unlock_irqrestore+0x14/0x24 > [ 358.875398] oom_kill_process+0x86/0x379 > [ 358.887838] out_of_memory+0x3a6/0x3ef > [ 358.899730] __alloc_pages_slowpath+0x86e/0xa1f > [ 358.913977] ? native_sched_clock+0x1a/0x37 > [ 358.927197] __alloc_pages_nodemask+0x134/0x1d4 > [ 358.941432] alloc_pages_current+0x8d/0x96 > [ 358.954343] bio_alloc_pages+0x29/0x6a > [ 358.966194] bch_writeback_thread+0x51c/0x6d4 [bcache] > [ 358.982206] ? write_dirty+0x90/0x90 [bcache] > [ 358.995878] kthread+0xfb/0x100 > [ 359.005899] ? init_completion+0x24/0x24 > [ 359.018242] ? do_fast_syscall_32+0xb7/0xfe > [ 359.031360] ret_from_fork+0x25/0x30 > [ 359.042723] Mem-Info: > [ 359.050529] active_anon:0 inactive_anon:2 isolated_anon:0 > [ 359.050529] active_file:306 inactive_file:163 isolated_file:0 > [ 359.050529] unevictable:0 dirty:0 writeback:0 unstable:0 > [ 359.050529] slab_reclaimable:3430 slab_unreclaimable:8034083 > [ 359.050529] mapped:1 shmem:2 pagetables:80 bounce:0 > [ 359.050529] free:51932 free_pcp:46 free_cma:3741 > [ 359.149971] Node 0 active_anon:0kB inactive_anon:8kB active_file:1128kB > inactive_file:892kB unevictable:0kB isolated(anon):0kB isolated(file):0kB > mapped:4kB dirty:0kB writeback:0kB shmem:8kB shmem_thp: 0kB shmem_pmdmapped: > 0kB anon_thp: 0kB writeback_tmp:0kB unstable:0kB all_unreclaimable? yes > [ 359.229593] Node 0 DMA free:15880kB min:32kB low:44kB high:56kB > active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:0kB > unevictable:0kB writepending:0kB present:15964kB managed:15880kB mlocked:0kB > kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB local_pcp:0kB > free_cma:0kB > [ 359.308570] lowmem_reserve[]: 0 3201 31832 31832 31832 > [ 359.324706] Node 0 DMA32 free:121124kB min:6788kB low:10064kB high:13340kB > active_anon:0kB inactive_anon:0kB active_file:100kB inactive_file:0kB > unevictable:0kB writepending:0kB present:3362068kB managed:3296500kB > mlocked:0kB kernel_stack:16kB pagetables:0kB bounce:0kB free_pcp:0kB > local_pcp:0kB free_cma:0kB > [ 359.408498] lowmem_reserve[]: 0 0 28631 28631 28631 > [ 359.423773] Node 0 Normal free:70792kB min:60760kB low:90092kB > high:119424kB active_anon:0kB inactive_anon:8kB active_file:780kB > inactive_file:808kB unevictable:0kB writepending:0kB present:29874176kB > managed:29337512kB mlocked:0kB kernel_stack:4608kB pagetables:320kB > bounce:0kB free_pcp:0kB local_pcp:0kB free_cma:14964kB > [ 359.511284] lowmem_reserve[]: 0 0 0 0 0 > [ 359.523514] Node 0 DMA: 0*4kB 1*8kB (U) 0*16kB 0*32kB 2*64kB (U) 1*128kB > (U) 1*256kB (U) 0*512kB 1*1024kB (U) 1*2048kB (M) 3*4096kB (M) = 15880kB > [ 359.564260] Node 0 DMA32: 3*4kB (UME) 3*8kB (ME) 4*16kB (UME) 6*32kB (UME) > 4*64kB (ME) 4*128kB (ME) 5*256kB (ME) 4*512kB (ME) 6*1024kB (UME) 4*2048kB > (UME) 25*4096kB (M) = 121124kB > [ 359.614116] Node 0 Normal: 559*4kB (UMEC) 272*8kB (ME) 163*16kB (UMEC) > 93*32kB (UMEC) 65*64kB (MEC) 71*128kB (UME) 37*256kB (ME) 18*512kB (UMC) > 8*1024kB (M) 4*2048kB (MC) 3*4096kB (C) = 70604kB > [ 359.667377] Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 > hugepages_size=2048kB > [ 359.693519] 456 total pagecache pages > [ 359.705331] 0 pages in swap cache > [ 359.716151] Swap cache stats: add 1184, delete 1184, find 4/8 > [ 359.734213] Free swap = 15610620kB > [ 359.745499] Total swap = 15616764kB > [ 359.756879] 8313052 pages RAM > [ 359.766596] 0 pages HighMem/MovableOnly > [ 359.778927] 150579 pages reserved > [ 359.789686] 4096 pages cma reserved > [ 359.801052] 0 pages hwpoisoned > [ 359.811026] [ pid ] uid tgid total_vm rss nr_ptes nr_pmds > swapents oom_score_adj name > [ 359.837419] [ 967] 0 967 936 0 6 2 32 > 0 init > [ 359.863819] [ 968] 0 968 941 1 5 2 98 > 0 rc > [ 359.889683] [ 1087] 0 1087 942 1 5 2 212 > -1000 udevd > [ 359.916457] [ 1294] 0 1294 917 1 5 2 60 > -1000 net.agent > [ 359.944236] [ 1340] 0 1340 917 1 5 2 59 > -1000 net.agent > [ 359.971915] [ 1750] 0 1750 918 1 5 2 59 > -1000 net.agent > [ 359.999603] [ 1915] 0 1915 587 0 5 2 31 > 0 bootlogd > [ 360.027033] [ 2442] 0 2442 942 0 5 2 211 > -1000 udevd > [ 360.053685] [ 2443] 0 2443 942 0 5 2 211 > -1000 udevd > [ 360.080467] [ 3023] 0 3023 1538 1 6 2 > 177 0 S13mountall.sh > [ 360.109446] [ 3078] 0 3078 1719 1 7 2 > 129 0 mount > [ 360.136111] [ 5722] 0 5722 558 0 5 2 16 > -1000 sleep > [ 360.162742] [ 5723] 0 5723 558 0 5 2 17 > -1000 sleep > [ 360.189358] [ 5724] 0 5724 558 0 5 2 17 > -1000 sleep > [ 360.215977] Out of memory: Kill process 3023 (S13mountall.sh) score 0 or > sacrifice child > [ 360.241102] Killed process 3078 (mount) total-vm:6876kB, anon-rss:0kB, > file-rss:4kB, shmem-rss:0kB > [ 360.276193] oom_reaper: reaped process 3078 (mount), now anon-rss:0kB, > file-rss:0kB, shmem-rss:0kB > [ 360.308435] bcache_writebac invoked oom-killer: > gfp_mask=0x14000c0(GFP_KERNEL), nodemask=(null), order=0, oom_score_adj=0 > [ 360.342339] bcache_writebac cpuset=/ mems_allowed=0 > [ 360.357757] CPU: 1 PID: 2339 Comm: bcache_writebac Tainted: G U > 4.13.0-rc5-amd64-stkreg-sysrq-20170902+ #2 > [ 360.390847] Hardware name: System manufacturer System Product Name/P8H67-M > PRO, BIOS 3904 04/27/2013 > [ 360.419010] Call Trace: > [ 360.427123] dump_stack+0x61/0x7d > [ 360.437815] dump_header+0x97/0x239 > [ 360.449000] ? _raw_spin_unlock_irqrestore+0x14/0x24 > [ 360.464705] oom_kill_process+0x86/0x379 > [ 360.477180] out_of_memory+0x3a6/0x3ef > [ 360.489120] __alloc_pages_slowpath+0x86e/0xa1f > [ 360.503360] ? native_sched_clock+0x1a/0x37 > [ 360.516712] __alloc_pages_nodemask+0x134/0x1d4 > [ 360.530950] alloc_pages_current+0x8d/0x96 > [ 360.543852] bio_alloc_pages+0x29/0x6a > [ 360.555696] bch_writeback_thread+0x51c/0x6d4 [bcache] > [ 360.571694] ? write_dirty+0x90/0x90 [bcache] > [ 360.585320] kthread+0xfb/0x100 > [ 360.595281] ? init_completion+0x24/0x24 > [ 360.607571] ? do_fast_syscall_32+0xb7/0xfe > [ 360.620725] ret_from_fork+0x25/0x30 > [ 360.632000] Mem-Info: > [ 360.639511] active_anon:0 inactive_anon:2 isolated_anon:0 > [ 360.639511] active_file:237 inactive_file:181 isolated_file:0 > [ 360.639511] unevictable:0 dirty:0 writeback:0 unstable:0 > [ 360.639511] slab_reclaimable:3428 slab_unreclaimable:8054968 > [ 360.639511] mapped:1 shmem:2 pagetables:80 bounce:0 > [ 360.639511] free:31221 free_pcp:20 free_cma:3741 > [ 360.738644] Node 0 active_anon:0kB inactive_anon:8kB active_file:1016kB > inactive_file:980kB unevictable:0kB isolated(anon):0kB isolated(file):0kB > mapped:4kB dirty:0kB writeback:0kB shmem:8kB shmem_thp: 0kB shmem_pmdmapped: > 0kB anon_thp: 0kB writeback_tmp:0kB unstable:0kB all_unreclaimable? no > [ 360.818057] Node 0 DMA free:15880kB min:32kB low:44kB high:56kB > active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:0kB > unevictable:0kB writepending:0kB present:15964kB managed:15880kB mlocked:0kB > kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB local_pcp:0kB > free_cma:0kB > [ 360.897260] lowmem_reserve[]: 0 3201 31832 31832 31832 > [ 360.913324] Node 0 DMA32 free:4760kB min:6788kB low:10064kB high:13340kB > active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:324kB > unevictable:0kB writepending:0kB present:3362068kB managed:3296500kB > mlocked:0kB kernel_stack:16kB pagetables:0kB bounce:0kB free_pcp:28kB > local_pcp:0kB free_cma:0kB > [ 360.968034] mount: page allocation failure: order:0, > mode:0x1604040(GFP_NOFS|__GFP_COMP|__GFP_NOTRACK), nodemask=(null) > [ 360.968038] mount cpuset=/ mems_allowed=0 > [ 360.968042] CPU: 0 PID: 3078 Comm: mount Tainted: G U > 4.13.0-rc5-amd64-stkreg-sysrq-20170902+ #2 > [ 360.968043] Hardware name: System manufacturer System Product Name/P8H67-M > PRO, BIOS 3904 04/27/2013 > [ 360.968044] Call Trace: > [ 360.968050] dump_stack+0x61/0x7d > [ 360.968052] warn_alloc+0xe4/0x15d > [ 360.968056] ? call_timer_fn+0x140/0x140 > [ 360.968058] __alloc_pages_slowpath+0x9a8/0xa1f > [ 360.968068] ? __rmqueue+0x285/0x297 > [ 360.968071] __alloc_pages_nodemask+0x134/0x1d4 > [ 360.968075] cache_grow_begin+0x95/0x26f > [ 360.968077] fallback_alloc+0x154/0x196 > [ 360.968079] ____cache_alloc_node+0xdd/0xe9 > [ 360.968081] kmem_cache_alloc_trace+0xa0/0xfc > [ 360.968084] add_tree_block+0x6a/0x1ac > [ 360.968086] build_ref_tree_for_root+0x19b/0x3a5 > [ 360.968088] btrfs_build_ref_tree+0x133/0x156 > [ 360.968090] open_ctree+0x1997/0x1fd2 > [ 360.968093] btrfs_mount+0x9d5/0xb2d > [ 360.968094] ? btrfs_mount+0x9d5/0xb2d > [ 360.968096] ? find_next_bit+0xb/0xd > [ 360.968099] mount_fs+0x67/0x111 > [ 360.968101] vfs_kern_mount+0x6b/0xd5 > [ 360.968102] btrfs_mount+0x1c3/0xb2d > [ 360.968103] ? find_next_bit+0xb/0xd > [ 360.968106] mount_fs+0x67/0x111 > [ 360.968107] vfs_kern_mount+0x6b/0xd5 > [ 360.968109] do_mount+0x6da/0x964 > [ 360.968111] ? slab_post_alloc_hook.isra.46+0xe/0x1d > [ 360.968113] compat_SyS_mount+0x185/0x1ae > [ 360.968116] do_fast_syscall_32+0xb7/0xfe > [ 360.968118] entry_SYSENTER_compat+0x4c/0x5b > [ 360.968119] RIP: 0023:0xf7f21c29 > [ 360.968120] RSP: 002b:00000000ffd733e0 EFLAGS: 00000297 ORIG_RAX: > 0000000000000015 > [ 360.968122] RAX: ffffffffffffffda RBX: 0000000008ff32c8 RCX: > 0000000008ff3118 > [ 360.968122] RDX: 0000000008ff3010 RSI: 00000000c0ed0400 RDI: > 0000000008ff6500 > [ 360.968123] RBP: 0000000000000000 R08: 0000000000000000 R09: > 0000000000000000 > [ 360.968124] R10: 0000000000000000 R11: 0000000000000000 R12: > 0000000000000000 > [ 360.968124] R13: 0000000000000000 R14: 0000000000000000 R15: > 0000000000000000 > [ 360.968126] Mem-Info: > [ 360.968130] active_anon:0 inactive_anon:2 isolated_anon:0 > [ 360.968130] active_file:333 inactive_file:144 isolated_file:0 > [ 360.968130] unevictable:0 dirty:0 writeback:0 unstable:0 > [ 360.968130] slab_reclaimable:3428 slab_unreclaimable:8082489 > [ 360.968130] mapped:1 shmem:2 pagetables:80 bounce:0 > [ 360.968130] free:3717 free_pcp:9 free_cma:3741 > [ 360.968132] Node 0 active_anon:0kB inactive_anon:8kB active_file:1332kB > inactive_file:576kB unevictable:0kB isolated(anon):0kB isolated(file):0kB > mapped:4kB dirty:0kB writeback:0kB shmem:8kB shmem_thp: 0kB shmem_pmdmapped: > 0kB anon_thp: 0kB writeback_tmp:0kB unstable:0kB all_unreclaimable? yes > [ 360.968133] Node 0 DMA free:0kB min:32kB low:44kB high:56kB > active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:0kB > unevictable:0kB writepending:0kB present:15964kB managed:15880kB mlocked:0kB > kernel_stack:0kB pagetables:0kB bounce:0kB free_pcp:0kB local_pcp:0kB > free_cma:0kB > [ 360.968136] lowmem_reserve[]: 0 3201 31832 31832 31832 > [ 360.968138] Node 0 DMA32 free:296kB min:6788kB low:10064kB high:13340kB > active_anon:0kB inactive_anon:0kB active_file:0kB inactive_file:292kB > unevictable:0kB writepending:0kB present:3362068kB managed:3296500kB > mlocked:0kB kernel_stack:16kB pagetables:0kB bounce:0kB free_pcp:0kB > local_pcp:0kB free_cma:0kB > [ 360.968141] lowmem_reserve[]: 0 0 28631 28631 28631 > [ 360.968143] Node 0 Normal free:14572kB min:60760kB low:90092kB > high:119424kB active_anon:0kB inactive_anon:8kB active_file:920kB > inactive_file:504kB unevictable:0kB writepending:0kB present:29874176kB > managed:29337512kB mlocked:0kB kernel_stack:4608kB pagetables:320kB > bounce:0kB free_pcp:36kB local_pcp:0kB free_cma:14964kB > [ 360.968146] lowmem_reserve[]: 0 0 0 0 0 > [ 360.968147] Node 0 DMA: 0*4kB 0*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB > 0*512kB 0*1024kB 0*2048kB 0*4096kB = 0kB > [ 360.968152] Node 0 DMA32: 0*4kB 0*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB > 0*512kB 0*1024kB 0*2048kB 0*4096kB = 0kB > [ 360.968157] Node 0 Normal: 1*4kB (C) 0*8kB 1*16kB (C) 1*32kB (C) 1*64kB > (C) 0*128kB 0*256kB 1*512kB (C) 0*1024kB 1*2048kB (C) 3*4096kB (C) = 14964kB > [ 360.968164] Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 > hugepages_size=2048kB > [ 360.968165] 495 total pagecache pages > [ 360.968167] 0 pages in swap cache > [ 360.968168] Swap cache stats: add 1184, delete 1184, find 4/8 > [ 360.968169] Free swap = 15611132kB > [ 360.968169] Total swap = 15616764kB > [ 360.968170] 8313052 pages RAM > [ 360.968170] 0 pages HighMem/MovableOnly > [ 360.968170] 150579 pages reserved > [ 360.968171] 4096 pages cma reserved > [ 360.968171] 0 pages hwpoisoned > [ 362.324699] lowmem_reserve[]: 0 0 28631 28631 28631 > [ 362.340147] Node 0 Normal free:2422448kB min:60760kB low:90092kB > high:119424kB active_anon:636kB inactive_anon:196kB active_file:3788kB > inactive_file:1424kB unevictable:0kB writepending:0kB present:29874176kB > managed:29337512kB mlocked:0kB kernel_stack:4608kB pagetables:324kB > bounce:0kB free_pcp:4100kB local_pcp:48kB free_cma:11468kB > [ 362.431162] lowmem_reserve[]: 0 0 0 0 0 > [ 362.443496] Node 0 DMA: 0*4kB 0*8kB 0*16kB 0*32kB 0*64kB 0*128kB 0*256kB > 0*512kB 0*1024kB 0*2048kB 0*4096kB = 0kB > [ 362.475115] Node 0 DMA32: 4469*4kB (U) 3639*8kB (U) 3116*16kB (U) > 1233*32kB (U) 64*64kB (U) 9*128kB (U) 4*256kB (U) 6*512kB (U) 3*1024kB (U) > 6*2048kB (U) 45*4096kB (U) = 345324kB > [ 362.524575] Node 0 Normal: 53138*4kB (UMC) 40392*8kB (UMC) 29104*16kB (UM) > 16364*32kB (U) 4513*64kB (UC) 658*128kB (UC) 25*256kB (U) 18*512kB (U) > 20*1024kB (UC) 19*2048kB (UC) 193*4096kB (UC) = 2763592kB > [ 362.580622] Node 0 hugepages_total=0 hugepages_free=0 hugepages_surp=0 > hugepages_size=2048kB > [ 362.606863] 1429 total pagecache pages > [ 362.619062] 96 pages in swap cache > [ 362.630199] Swap cache stats: add 1396, delete 1300, find 237/380 > [ 362.649433] Free swap = 15611132kB > [ 362.660833] Total swap = 15616764kB > [ 362.672274] 8313052 pages RAM > [ 362.682133] 0 pages HighMem/MovableOnly > [ 362.694909] 150579 pages reserved > [ 362.705741] 4096 pages cma reserved > [ 362.717084] 0 pages hwpoisoned > [ 362.727099] [ pid ] uid tgid total_vm rss nr_ptes nr_pmds > swapents oom_score_adj name > [ 362.753547] [ 967] 0 967 936 0 6 2 32 > 0 init > [ 362.779963] [ 968] 0 968 941 1 5 2 98 > 0 rc > [ 362.805846] [ 1087] 0 1087 942 1 5 2 212 > -1000 udevd > [ 362.832511] [ 1294] 0 1294 917 421 5 2 24 > -1000 net.agent > [ 362.860203] [ 1340] 0 1340 917 396 5 2 28 > -1000 net.agent > [ 362.887851] [ 1750] 0 1750 918 419 5 2 25 > -1000 net.agent > [ 362.915478] [ 1915] 0 1915 587 0 5 2 31 > 0 bootlogd > [ 362.942839] [ 2442] 0 2442 942 0 5 2 211 > -1000 udevd > [ 362.969390] [ 2443] 0 2443 942 0 5 2 211 > -1000 udevd > [ 362.995922] [ 3023] 0 3023 1538 1 6 2 > 177 0 S13mountall.sh > [ 363.024797] [ 3078] 0 3078 1719 0 7 2 > 0 0 mount > [ 363.051309] [ 5743] 0 5743 558 147 5 2 0 > -1000 sleep > [ 363.077802] [ 5744] 0 5744 558 148 5 2 0 > -1000 sleep > [ 363.104305] [ 5745] 0 5745 558 143 5 2 0 > -1000 sleep > [ 363.130752] Out of memory: Kill process 3023 (S13mountall.sh) score 0 or > sacrifice child > [ 363.155660] Killed process 3023 (S13mountall.sh) total-vm:6152kB, > anon-rss:0kB, file-rss:4kB, shmem-rss:0kB > /etc/init.d/rc: line 120: 3023 Killed $debug "$script" $action > > -- > "A mouse is a device used to point at the xterm you want to type in" - A.S.R. > Microsoft is to operating systems .... > .... what McDonalds is to gourmet cooking > Home page: > https://urldefense.proofpoint.com/v2/url?u=http-3A__marc.merlins.org_&d=DwIBAg&c=5VD0RTtNlTh3ycd41b3MUw&r=sDzg6MvHymKOUgI8SFIm4Q&m=1aDQg12_YvSWTRwtKEuju2jwfwBQHWUmF1TFzisZwyE&s=gOQVCOu1vW2YKYAvS2imou0jsDaSNerp6_GvMVfCh5Q&e= > | PGP 1024R/763BE901 -- To unsubscribe from this list: send the line "unsubscribe linux-btrfs" in the body of a message to majord...@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html