All of lore.kernel.org
 help / color / mirror / Atom feed
From: Joe Landman <landman@scalableinformatics.com>
To: linux-xfs@oss.sgi.com
Subject: A corruption that seems to span a few kernels
Date: Fri, 03 Feb 2012 15:02:14 -0500	[thread overview]
Message-ID: <4F2C3D46.1010509@scalableinformatics.com> (raw)

XFS file system, built using a 2.6.32.41 kernel.  External journals.

repair the file system, mount, turn on gluster (3.2.5), do a find, and 
get a corruption.  Actually it looks like xfs_repair doesn't fix the 
problem.

Rinse repeat, reproduce.  Works (procedure to generate the corruption) 
in 2.6.32.41.scalable, 2.6.39.1, 3.2.2

[  428.457044] XFS (sdc2): corrupt dinode 54105173, extent total = 1, 
nblocks = 0.
[  428.464596] ffff880bde999500: 49 4e 81 a4 01 02 00 01 00 00 04 65 00 
00 07 df  IN.........e....
[  428.473587] XFS (sdc2): Internal error xfs_iformat(1) at line 319 of 
file fs/xfs/xfs_inode.c.  Caller 0xffffffff8127b738
[  428.473589]
[  428.486388] Pid: 7562, comm: glusterfsd Not tainted 3.2.2.scalable #1
[  428.493014] Call Trace:
[  428.495544]  [<ffffffff812361aa>] xfs_error_report+0x3a/0x40
[  428.501391]  [<ffffffff8127b738>] ? xfs_iread+0x118/0x1a0
[  428.506894]  [<ffffffff81236208>] xfs_corruption_error+0x58/0x80
[  428.513027]  [<ffffffff8127b4b1>] xfs_iformat+0x401/0x570
[  428.518491]  [<ffffffff8127b738>] ? xfs_iread+0x118/0x1a0
[  428.524003]  [<ffffffff8127b738>] xfs_iread+0x118/0x1a0
[  428.529292]  [<ffffffff8123aba3>] xfs_iget+0x2d3/0x8b0
[  428.534537]  [<ffffffff8123a252>] ? xfs_iunlock+0x92/0x130
[  428.540122]  [<ffffffff81246c68>] xfs_lookup+0xb8/0x140
[  428.545413]  [<ffffffff8123fc59>] xfs_vn_lookup+0x59/0xa0
[  428.550922]  [<ffffffff8113f545>] ? d_alloc+0x75/0x90
[  428.556034]  [<ffffffff81134d14>] d_alloc_and_lookup+0x44/0x80
[  428.561976]  [<ffffffff81135213>] do_lookup+0x243/0x350
[  428.567326]  [<ffffffff8113867a>] path_lookupat+0xea/0x740
[  428.572942]  [<ffffffff8124fea2>] ? xfs_attr_get+0xb2/0xc0
[  428.578489]  [<ffffffff81138d00>] do_path_lookup+0x30/0xc0
[  428.584089]  [<ffffffff81139974>] user_path_at_empty+0x54/0xa0
[  428.589984]  [<ffffffff8111cf42>] ? kmem_cache_free+0x22/0x120
[  428.595932]  [<ffffffff81137901>] ? putname+0x31/0x50
[  428.601091]  [<ffffffff8113997f>] ? user_path_at_empty+0x5f/0xa0
[  428.607190]  [<ffffffff811399cc>] user_path_at+0xc/0x10
[  428.612586]  [<ffffffff8112ef46>] vfs_fstatat+0x46/0x80
[  428.617868]  [<ffffffff8112efe9>] vfs_lstat+0x19/0x20
[  428.623068]  [<ffffffff8112f00f>] sys_newlstat+0x1f/0x50
[  428.628626]  [<ffffffff8109e2bd>] ? audit_syscall_entry+0x16d/0x1d0
[  428.635009]  [<ffffffff8153f752>] system_call_fastpath+0x16/0x1b
[  428.641352] XFS (sdc2): Corruption detected. Unmount and run xfs_repair

[root@jr4-3 ~]# /etc/init.d/glusterd stop
Stopping glusterd:                                         [  OK  ]
[root@jr4-3 ~]# umount /data/brick-sdc2
[root@jr4-3 ~]# nohup xfs_repair -vvv -l /dev/md1 /dev/sdc2 > 
/tmp/out2.sdc 2>&1 &
[1] 7689

xfs_repair runs.  File system becomes normal.  Can reboot or remain in 
the same system.  Select any of the kernels.  Mount the file system.

I haven't checked whether this only happens with Gluster yet or not, 
working on it next ... will do the find w/o gluster on the backing 
store.  See if it croaks.

Currently booted into 3.2.2, can boot into something else.

Any hints?  I can reproduce it quite well, and xfs_repair seems to work 
... (repeated passes don't seem to help).

[root@jr4-3 ~]# grep "corrupt dinode 54105173" /var/log/messages
Feb  2 23:08:46 jr4-3 kernel: [ 1548.511502] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  2 23:13:32 jr4-3 kernel: [ 1834.627251] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  2 23:37:44 jr4-3 kernel: [ 3286.598877] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 00:07:43 jr4-3 kernel: [ 5085.429344] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 00:37:44 jr4-3 kernel: [ 6886.552328] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 01:07:43 jr4-3 kernel: [ 8686.384728] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 01:37:47 jr4-3 kernel: [10490.113301] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 02:07:46 jr4-3 kernel: [12289.248980] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 02:37:43 jr4-3 kernel: [14086.210521] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 03:07:45 jr4-3 kernel: [15888.798065] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 03:37:43 jr4-3 kernel: [17686.388882] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 04:04:06 jr4-3 kernel: [19269.902522] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 04:08:04 jr4-3 kernel: [19507.447343] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 04:38:11 jr4-3 kernel: [21314.248443] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 05:07:43 jr4-3 kernel: [23086.714157] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 05:37:43 jr4-3 kernel: [24886.444238] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 06:07:43 jr4-3 kernel: [26686.740589] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 06:37:45 jr4-3 kernel: [28488.946147] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 07:07:42 jr4-3 kernel: [30286.417803] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 07:37:42 jr4-3 kernel: [32085.847705] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 08:08:01 jr4-3 kernel: [33904.979795] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 08:37:46 jr4-3 kernel: [35690.043019] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 08:47:19 jr4-3 kernel: [36263.597170] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 09:07:42 jr4-3 kernel: [37486.293617] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 09:37:42 jr4-3 kernel: [39285.987621] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 10:07:42 jr4-3 kernel: [41086.440845] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 10:37:55 jr4-3 kernel: [42899.537075] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 11:08:24 jr4-3 kernel: [  988.628970] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 13:08:20 jr4-3 kernel: [ 2531.085884] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 13:10:13 jr4-3 kernel: [ 2643.954262] Filesystem "sdc2": corrupt 
dinode 54105173, extent total = 1, nblocks = 0.  Unmount and run xfs_repair.
Feb  3 08:38:20 jr4-3 kernel: [  428.457044] XFS (sdc2): corrupt dinode 
54105173, extent total = 1, nblocks = 0.


Any clues/hints/suggestions?  Zero out that dinode (and if so, how?) 
Let me know if you want any additional information from this system.

Its a large RAID6, with battery backed ECC cache.  No disk events reported.

This appeared after finishing the xfs_repair

[root@jr4-3 ~]# [ 1102.898890] scsi_verify_blk_ioctl: 56 callbacks 
suppressed
[ 1102.904486] xfs_repair: sending ioctl 1261 to a partition!
[ 1102.910286] xfs_repair: sending ioctl 1261 to a partition!


Output from xfs_repair below.  Notes are in phase 3 and 4

phase 3:
data fork in regular inode 54105173 claims used block 6745835296

phase 4:
data fork in regular inode 54105173 claims used block 6745835296

xfs_repair doesn't seem to fix this, as a second pass through still 
indicates a problem.

First pass:

[root@jr4-3 ~]# cat !$
cat /tmp/out2.sdc
Phase 1 - find and verify superblock...
         - max_mem = 37094007, icount = 5448960, imem = 21285, dblock = 
4391112384, dmem = 2144097
         - block cache size set to 4359824 entries
Phase 2 - using external log on /dev/md1
         - zero log...
zero_log: head block 48836 tail block 48836
         - scan filesystem freespace and inode maps...
         - found root inode chunk
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 3278
Active entries = 3278
Hash table size = 544978
Hits = 0
Misses = 3278
Hit ratio =  0.00
MRU 0 entries =   3278 (100%)
MRU 1 entries =      0 (  0%)
MRU 2 entries =      0 (  0%)
MRU 3 entries =      0 (  0%)
MRU 4 entries =      0 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =      0 (  0%)
MRU 7 entries =      0 (  0%)
MRU 8 entries =      0 (  0%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      0 (  0%)
MRU 12 entries =      0 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 541912 (  0%)
Hash buckets with   1 entries   2903 ( 88%)
Hash buckets with   2 entries    129 (  7%)
Hash buckets with   3 entries     21 (  1%)
Hash buckets with   4 entries     11 (  1%)
Hash buckets with   5 entries      2 (  0%)
Phase 3 - for each AG...
         - scan and clear agi unlinked lists...
         - process known inodes and perform inode discovery...
         - agno = 0
data fork in regular inode 54105173 claims used block 6745835296
         - agno = 1
         - agno = 2
         - agno = 3
         - agno = 4
         - agno = 5
         - agno = 6
         - agno = 7
         - agno = 8
         - agno = 9
         - agno = 10
         - agno = 11
         - agno = 12
         - agno = 13
         - agno = 14
         - agno = 15
         - agno = 16
         - agno = 17
         - agno = 18
         - agno = 19
         - agno = 20
         - agno = 21
         - agno = 22
         - agno = 23
         - agno = 24
         - agno = 25
         - agno = 26
         - agno = 27
         - agno = 28
         - agno = 29
         - agno = 30
         - agno = 31
         - process newly discovered inodes...
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 1052814
Active entries = 1052814
Hash table size = 544978
Hits = 302945
Misses = 1052814
Hit ratio = 22.35
MRU 0 entries = 851716 ( 80%)
MRU 1 entries =   6724 (  0%)
MRU 2 entries =  68352 (  6%)
MRU 3 entries = 108276 ( 10%)
MRU 4 entries =   5278 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =  12339 (  1%)
MRU 7 entries =     16 (  0%)
MRU 8 entries =      0 (  0%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      3 (  0%)
MRU 12 entries =    110 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 206656 (  0%)
Hash buckets with   1 entries  86130 (  8%)
Hash buckets with   2 entries  71589 ( 13%)
Hash buckets with   3 entries  20312 (  5%)
Hash buckets with   4 entries  99262 ( 37%)
Hash buckets with   5 entries  25665 ( 12%)
Hash buckets with   6 entries  21611 ( 12%)
Hash buckets with   7 entries   3104 (  2%)
Hash buckets with   8 entries  10077 (  7%)
Hash buckets with   9 entries    535 (  0%)
Hash buckets with  10 entries     35 (  0%)
Hash buckets with  11 entries      2 (  0%)
Phase 4 - check for duplicate blocks...
         - setting up duplicate extent list...
         - check for inodes claiming duplicate blocks...
         - agno = 0
         - agno = 1
         - agno = 2
         - agno = 3
         - agno = 4
         - agno = 5
         - agno = 6
         - agno = 7
         - agno = 8
         - agno = 9
         - agno = 10
         - agno = 11
         - agno = 12
         - agno = 14
         - agno = 15
         - agno = 18
         - agno = 16
         - agno = 20
         - agno = 22
         - agno = 19
         - agno = 25
         - agno = 26
         - agno = 21
         - agno = 29
         - agno = 24
         - agno = 31
         - agno = 17
         - agno = 27
         - agno = 28
         - agno = 23
         - agno = 30
         - agno = 13
data fork in regular inode 54105173 claims used block 6745835296
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 1052814
Active entries = 1052814
Hash table size = 544978
Hits = 646498
Misses = 1052814
Hit ratio = 38.04
MRU 0 entries = 1052701 ( 99%)
MRU 1 entries =      0 (  0%)
MRU 2 entries =      0 (  0%)
MRU 3 entries =      0 (  0%)
MRU 4 entries =      0 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =      0 (  0%)
MRU 7 entries =      0 (  0%)
MRU 8 entries =      0 (  0%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      3 (  0%)
MRU 12 entries =    110 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 206656 (  0%)
Hash buckets with   1 entries  86130 (  8%)
Hash buckets with   2 entries  71589 ( 13%)
Hash buckets with   3 entries  20312 (  5%)
Hash buckets with   4 entries  99262 ( 37%)
Hash buckets with   5 entries  25665 ( 12%)
Hash buckets with   6 entries  21611 ( 12%)
Hash buckets with   7 entries   3104 (  2%)
Hash buckets with   8 entries  10077 (  7%)
Hash buckets with   9 entries    535 (  0%)
Hash buckets with  10 entries     35 (  0%)
Hash buckets with  11 entries      2 (  0%)
Phase 5 - rebuild AG headers and trees...
         - agno = 0
         - agno = 1
         - agno = 2
         - agno = 3
         - agno = 4
         - agno = 5
         - agno = 6
         - agno = 7
         - agno = 8
         - agno = 9
         - agno = 10
         - agno = 11
         - agno = 12
         - agno = 13
         - agno = 14
         - agno = 15
         - agno = 16
         - agno = 17
         - agno = 18
         - agno = 19
         - agno = 20
         - agno = 21
         - agno = 22
         - agno = 23
         - agno = 24
         - agno = 25
         - agno = 26
         - agno = 27
         - agno = 28
         - agno = 29
         - agno = 30
         - agno = 31
         - reset superblock...
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 1052814
Active entries = 1052814
Hash table size = 544978
Hits = 649707
Misses = 1052814
Hit ratio = 38.16
MRU 0 entries = 1052701 ( 99%)
MRU 1 entries =      0 (  0%)
MRU 2 entries =      0 (  0%)
MRU 3 entries =      0 (  0%)
MRU 4 entries =      0 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =      0 (  0%)
MRU 7 entries =      0 (  0%)
MRU 8 entries =      0 (  0%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      3 (  0%)
MRU 12 entries =    110 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 206656 (  0%)
Hash buckets with   1 entries  86130 (  8%)
Hash buckets with   2 entries  71589 ( 13%)
Hash buckets with   3 entries  20312 (  5%)
Hash buckets with   4 entries  99262 ( 37%)
Hash buckets with   5 entries  25665 ( 12%)
Hash buckets with   6 entries  21611 ( 12%)
Hash buckets with   7 entries   3104 (  2%)
Hash buckets with   8 entries  10077 (  7%)
Hash buckets with   9 entries    535 (  0%)
Hash buckets with  10 entries     35 (  0%)
Hash buckets with  11 entries      2 (  0%)
Phase 6 - check inode connectivity...
         - resetting contents of realtime bitmap and summary inodes
         - traversing filesystem ...
         - agno = 0
         - agno = 1
         - agno = 2
         - agno = 3
         - agno = 4
         - agno = 5
         - agno = 6
         - agno = 7
         - agno = 8
         - agno = 9
         - agno = 10
         - agno = 11
         - agno = 12
         - agno = 13
         - agno = 14
         - agno = 15
         - agno = 16
         - agno = 17
         - agno = 18
         - agno = 19
         - agno = 20
         - agno = 21
         - agno = 22
         - agno = 23
         - agno = 24
         - agno = 25
         - agno = 26
         - agno = 27
         - agno = 28
         - agno = 29
         - agno = 30
         - agno = 31
         - traversal finished ...
         - moving disconnected inodes to lost+found ...
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 1052845
Active entries = 1052845
Hash table size = 544978
Hits = 1854913
Misses = 1052845
Hit ratio = 63.79
MRU 0 entries = 1016092 ( 96%)
MRU 1 entries =      0 (  0%)
MRU 2 entries =      0 (  0%)
MRU 3 entries =      3 (  0%)
MRU 4 entries =    141 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =      0 (  0%)
MRU 7 entries =  11363 (  1%)
MRU 8 entries =  25246 (  2%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      0 (  0%)
MRU 12 entries =      0 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 206646 (  0%)
Hash buckets with   1 entries  86134 (  8%)
Hash buckets with   2 entries  71593 ( 13%)
Hash buckets with   3 entries  20312 (  5%)
Hash buckets with   4 entries  99256 ( 37%)
Hash buckets with   5 entries  25670 ( 12%)
Hash buckets with   6 entries  21614 ( 12%)
Hash buckets with   7 entries   3104 (  2%)
Hash buckets with   8 entries  10077 (  7%)
Hash buckets with   9 entries    535 (  0%)
Hash buckets with  10 entries     35 (  0%)
Hash buckets with  11 entries      2 (  0%)
Phase 7 - verify and correct link counts...
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 1052845
Active entries = 1052845
Hash table size = 544978
Hits = 1854913
Misses = 1052845
Hit ratio = 63.79
MRU 0 entries = 1016092 ( 96%)
MRU 1 entries =      0 (  0%)
MRU 2 entries =      0 (  0%)
MRU 3 entries =      3 (  0%)
MRU 4 entries =    141 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =      0 (  0%)
MRU 7 entries =  11363 (  1%)
MRU 8 entries =  25246 (  2%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      0 (  0%)
MRU 12 entries =      0 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 206646 (  0%)
Hash buckets with   1 entries  86134 (  8%)
Hash buckets with   2 entries  71593 ( 13%)
Hash buckets with   3 entries  20312 (  5%)
Hash buckets with   4 entries  99256 ( 37%)
Hash buckets with   5 entries  25670 ( 12%)
Hash buckets with   6 entries  21614 ( 12%)
Hash buckets with   7 entries   3104 (  2%)
Hash buckets with   8 entries  10077 (  7%)
Hash buckets with   9 entries    535 (  0%)
Hash buckets with  10 entries     35 (  0%)
Hash buckets with  11 entries      2 (  0%)

         XFS_REPAIR Summary    Fri Feb  3 08:49:34 2012

Phase		Start		End		Duration
Phase 1:	02/03 08:43:06	02/03 08:43:06	
Phase 2:	02/03 08:43:06	02/03 08:43:11	5 seconds
Phase 3:	02/03 08:43:11	02/03 08:48:48	5 minutes, 37 seconds
Phase 4:	02/03 08:48:48	02/03 08:49:26	38 seconds
Phase 5:	02/03 08:49:26	02/03 08:49:27	1 second
Phase 6:	02/03 08:49:27	02/03 08:49:33	6 seconds
Phase 7:	02/03 08:49:33	02/03 08:49:33	

Total run time: 6 minutes, 27 seconds
done


Second pass:

[root@jr4-3 ~]# cat /tmp/out3.sdc
Phase 1 - find and verify superblock...
         - max_mem = 37094007, icount = 5448960, imem = 21285, dblock = 
4391112384, dmem = 2144097
         - block cache size set to 4359824 entries
Phase 2 - using external log on /dev/md1
         - zero log...
zero_log: head block 2 tail block 2
         - scan filesystem freespace and inode maps...
         - found root inode chunk
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 3240
Active entries = 3240
Hash table size = 544978
Hits = 0
Misses = 3240
Hit ratio =  0.00
MRU 0 entries =   3240 (100%)
MRU 1 entries =      0 (  0%)
MRU 2 entries =      0 (  0%)
MRU 3 entries =      0 (  0%)
MRU 4 entries =      0 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =      0 (  0%)
MRU 7 entries =      0 (  0%)
MRU 8 entries =      0 (  0%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      0 (  0%)
MRU 12 entries =      0 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 541938 (  0%)
Hash buckets with   1 entries   2881 ( 88%)
Hash buckets with   2 entries    127 (  7%)
Hash buckets with   3 entries     23 (  2%)
Hash buckets with   4 entries      9 (  1%)
Phase 3 - for each AG...
         - scan and clear agi unlinked lists...
         - process known inodes and perform inode discovery...
         - agno = 0
data fork in regular inode 54105173 claims used block 6745835296
         - agno = 1
         - agno = 2
         - agno = 3
         - agno = 4
         - agno = 5
         - agno = 6
         - agno = 7
         - agno = 8
         - agno = 9
         - agno = 10
         - agno = 11
         - agno = 12
         - agno = 13
         - agno = 14
         - agno = 15
         - agno = 16
         - agno = 17
         - agno = 18
         - agno = 19
         - agno = 20
         - agno = 21
         - agno = 22
         - agno = 23
         - agno = 24
         - agno = 25
         - agno = 26
         - agno = 27
         - agno = 28
         - agno = 29
         - agno = 30
         - agno = 31
         - process newly discovered inodes...
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 1052776
Active entries = 1052776
Hash table size = 544978
Hits = 302945
Misses = 1052776
Hit ratio = 22.35
MRU 0 entries = 851678 ( 80%)
MRU 1 entries =   6724 (  0%)
MRU 2 entries =  68352 (  6%)
MRU 3 entries = 107924 ( 10%)
MRU 4 entries =   5314 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =  12655 (  1%)
MRU 7 entries =     16 (  0%)
MRU 8 entries =      0 (  0%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      3 (  0%)
MRU 12 entries =    110 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 206666 (  0%)
Hash buckets with   1 entries  86129 (  8%)
Hash buckets with   2 entries  71585 ( 13%)
Hash buckets with   3 entries  20311 (  5%)
Hash buckets with   4 entries  99263 ( 37%)
Hash buckets with   5 entries  25662 ( 12%)
Hash buckets with   6 entries  21611 ( 12%)
Hash buckets with   7 entries   3103 (  2%)
Hash buckets with   8 entries  10076 (  7%)
Hash buckets with   9 entries    535 (  0%)
Hash buckets with  10 entries     35 (  0%)
Hash buckets with  11 entries      2 (  0%)
Phase 4 - check for duplicate blocks...
         - setting up duplicate extent list...
         - check for inodes claiming duplicate blocks...
         - agno = 0
         - agno = 2
         - agno = 5
         - agno = 7
         - agno = 1
         - agno = 3
         - agno = 4
         - agno = 11
         - agno = 8
         - agno = 14
         - agno = 15
         - agno = 9
         - agno = 17
         - agno = 18
         - agno = 19
         - agno = 10
         - agno = 21
         - agno = 22
         - agno = 23
         - agno = 24
         - agno = 6
         - agno = 12
         - agno = 25
         - agno = 27
         - agno = 26
         - agno = 20
         - agno = 28
         - agno = 16
         - agno = 31
         - agno = 13
         - agno = 29
         - agno = 30
data fork in regular inode 54105173 claims used block 6745835296
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 1052776
Active entries = 1052776
Hash table size = 544978
Hits = 646498
Misses = 1052776
Hit ratio = 38.05
MRU 0 entries = 1052663 ( 99%)
MRU 1 entries =      0 (  0%)
MRU 2 entries =      0 (  0%)
MRU 3 entries =      0 (  0%)
MRU 4 entries =      0 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =      0 (  0%)
MRU 7 entries =      0 (  0%)
MRU 8 entries =      0 (  0%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      3 (  0%)
MRU 12 entries =    110 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 206666 (  0%)
Hash buckets with   1 entries  86129 (  8%)
Hash buckets with   2 entries  71585 ( 13%)
Hash buckets with   3 entries  20311 (  5%)
Hash buckets with   4 entries  99263 ( 37%)
Hash buckets with   5 entries  25662 ( 12%)
Hash buckets with   6 entries  21611 ( 12%)
Hash buckets with   7 entries   3103 (  2%)
Hash buckets with   8 entries  10076 (  7%)
Hash buckets with   9 entries    535 (  0%)
Hash buckets with  10 entries     35 (  0%)
Hash buckets with  11 entries      2 (  0%)
Phase 5 - rebuild AG headers and trees...
         - agno = 0
         - agno = 1
         - agno = 2
         - agno = 3
         - agno = 4
         - agno = 5
         - agno = 6
         - agno = 7
         - agno = 8
         - agno = 9
         - agno = 10
         - agno = 11
         - agno = 12
         - agno = 13
         - agno = 14
         - agno = 15
         - agno = 16
         - agno = 17
         - agno = 18
         - agno = 19
         - agno = 20
         - agno = 21
         - agno = 22
         - agno = 23
         - agno = 24
         - agno = 25
         - agno = 26
         - agno = 27
         - agno = 28
         - agno = 29
         - agno = 30
         - agno = 31
         - reset superblock...
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 1052776
Active entries = 1052776
Hash table size = 544978
Hits = 649707
Misses = 1052776
Hit ratio = 38.16
MRU 0 entries = 1052663 ( 99%)
MRU 1 entries =      0 (  0%)
MRU 2 entries =      0 (  0%)
MRU 3 entries =      0 (  0%)
MRU 4 entries =      0 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =      0 (  0%)
MRU 7 entries =      0 (  0%)
MRU 8 entries =      0 (  0%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      3 (  0%)
MRU 12 entries =    110 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 206666 (  0%)
Hash buckets with   1 entries  86129 (  8%)
Hash buckets with   2 entries  71585 ( 13%)
Hash buckets with   3 entries  20311 (  5%)
Hash buckets with   4 entries  99263 ( 37%)
Hash buckets with   5 entries  25662 ( 12%)
Hash buckets with   6 entries  21611 ( 12%)
Hash buckets with   7 entries   3103 (  2%)
Hash buckets with   8 entries  10076 (  7%)
Hash buckets with   9 entries    535 (  0%)
Hash buckets with  10 entries     35 (  0%)
Hash buckets with  11 entries      2 (  0%)
Phase 6 - check inode connectivity...
         - resetting contents of realtime bitmap and summary inodes
         - traversing filesystem ...
         - agno = 0
         - agno = 1
         - agno = 2
         - agno = 3
         - agno = 4
         - agno = 5
         - agno = 6
         - agno = 7
         - agno = 8
         - agno = 9
         - agno = 10
         - agno = 11
         - agno = 12
         - agno = 13
         - agno = 14
         - agno = 15
         - agno = 16
         - agno = 17
         - agno = 18
         - agno = 19
         - agno = 20
         - agno = 21
         - agno = 22
         - agno = 23
         - agno = 24
         - agno = 25
         - agno = 26
         - agno = 27
         - agno = 28
         - agno = 29
         - agno = 30
         - agno = 31
         - traversal finished ...
         - moving disconnected inodes to lost+found ...
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 1052807
Active entries = 1052807
Hash table size = 544978
Hits = 1854913
Misses = 1052807
Hit ratio = 63.79
MRU 0 entries = 1016054 ( 96%)
MRU 1 entries =      0 (  0%)
MRU 2 entries =      0 (  0%)
MRU 3 entries =      3 (  0%)
MRU 4 entries =    141 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =      0 (  0%)
MRU 7 entries =  11363 (  1%)
MRU 8 entries =  25246 (  2%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      0 (  0%)
MRU 12 entries =      0 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 206656 (  0%)
Hash buckets with   1 entries  86133 (  8%)
Hash buckets with   2 entries  71589 ( 13%)
Hash buckets with   3 entries  20311 (  5%)
Hash buckets with   4 entries  99257 ( 37%)
Hash buckets with   5 entries  25667 ( 12%)
Hash buckets with   6 entries  21614 ( 12%)
Hash buckets with   7 entries   3103 (  2%)
Hash buckets with   8 entries  10076 (  7%)
Hash buckets with   9 entries    535 (  0%)
Hash buckets with  10 entries     35 (  0%)
Hash buckets with  11 entries      2 (  0%)
Phase 7 - verify and correct link counts...
libxfs_bcache: 0x6814c0
Max supported entries = 4359824
Max utilized entries = 1052807
Active entries = 1052807
Hash table size = 544978
Hits = 1854913
Misses = 1052807
Hit ratio = 63.79
MRU 0 entries = 1016054 ( 96%)
MRU 1 entries =      0 (  0%)
MRU 2 entries =      0 (  0%)
MRU 3 entries =      3 (  0%)
MRU 4 entries =    141 (  0%)
MRU 5 entries =      0 (  0%)
MRU 6 entries =      0 (  0%)
MRU 7 entries =  11363 (  1%)
MRU 8 entries =  25246 (  2%)
MRU 9 entries =      0 (  0%)
MRU 10 entries =      0 (  0%)
MRU 11 entries =      0 (  0%)
MRU 12 entries =      0 (  0%)
MRU 13 entries =      0 (  0%)
MRU 14 entries =      0 (  0%)
MRU 15 entries =      0 (  0%)
Hash buckets with   0 entries 206656 (  0%)
Hash buckets with   1 entries  86133 (  8%)
Hash buckets with   2 entries  71589 ( 13%)
Hash buckets with   3 entries  20311 (  5%)
Hash buckets with   4 entries  99257 ( 37%)
Hash buckets with   5 entries  25667 ( 12%)
Hash buckets with   6 entries  21614 ( 12%)
Hash buckets with   7 entries   3103 (  2%)
Hash buckets with   8 entries  10076 (  7%)
Hash buckets with   9 entries    535 (  0%)
Hash buckets with  10 entries     35 (  0%)
Hash buckets with  11 entries      2 (  0%)

         XFS_REPAIR Summary    Fri Feb  3 09:00:02 2012

Phase		Start		End		Duration
Phase 1:	02/03 08:53:37	02/03 08:53:37	
Phase 2:	02/03 08:53:37	02/03 08:53:38	1 second
Phase 3:	02/03 08:53:38	02/03 08:59:16	5 minutes, 38 seconds
Phase 4:	02/03 08:59:16	02/03 08:59:54	38 seconds
Phase 5:	02/03 08:59:54	02/03 08:59:55	1 second
Phase 6:	02/03 08:59:55	02/03 09:00:01	6 seconds
Phase 7:	02/03 09:00:01	02/03 09:00:01	

Total run time: 6 minutes, 24 seconds
done



-- 
Joseph Landman, Ph.D
Founder and CEO
Scalable Informatics Inc.
email: landman@scalableinformatics.com
web  : http://scalableinformatics.com
        http://scalableinformatics.com/sicluster
phone: +1 734 786 8423 x121
fax  : +1 866 888 3112
cell : +1 734 612 4615

_______________________________________________
xfs mailing list
xfs@oss.sgi.com
http://oss.sgi.com/mailman/listinfo/xfs

             reply	other threads:[~2012-02-03 20:02 UTC|newest]

Thread overview: 3+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2012-02-03 20:02 Joe Landman [this message]
2012-02-03 21:27 ` A corruption that seems to span a few kernels Christoph Hellwig
2012-02-03 21:31   ` Joe Landman

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=4F2C3D46.1010509@scalableinformatics.com \
    --to=landman@scalableinformatics.com \
    --cc=linux-xfs@oss.sgi.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.