[Gluster-users] Metadata filesystem XFS gluster 3.6

[Félix de Lelelis]

Hi,

I had a problem with a filesystem xfs on gluster. The filesystem metadata
was filled:

Mar 27 13:58:18 srv-vln-des2 kernel: device-mapper: space map metadata:
unable to allocate new metadata block
Mar 27 13:58:18 srv-vln-des2 kernel: device-mapper: thin: 252:2: metadata
operation 'dm_thin_insert_block' failed: error = -28
Mar 27 13:58:18 srv-vln-des2 kernel: device-mapper: thin: 252:2: aborting
current metadata transaction
Mar 27 13:58:18 srv-vln-des2 kernel: device-mapper: thin: 252:2: switching
pool to read-only mode
Mar 27 13:58:18 srv-vln-des2 kernel: XFS (dm-4): metadata I/O error: block
0x701830 ("xfs_buf_iodone_callbacks") error 5 numblks 8
Mar 27 13:58:18 srv-vln-des2 kernel: attempt to access beyond end of device
Mar 27 13:58:18 srv-vln-des2 kernel: dm-0: rw=0, want=562056, limit=24576
Mar 27 13:58:18 srv-vln-des2 kernel: device-mapper: thin:
process_bio_read_only: dm_thin_find_block() failed: error = -5
Mar 27 13:58:18 srv-vln-des2 kernel: attempt to access beyond end of device
Mar 27 13:58:18 srv-vln-des2 kernel: dm-0: rw=0, want=562056, limit=24576
Mar 27 13:58:18 srv-vln-des2 kernel: device-mapper: thin:
process_bio_read_only: dm_thin_find_block() failed: error = -5
Mar 27 13:58:18 srv-vln-des2 kernel: XFS (dm-4): metadata I/O error: block
0x68047c ("xlog_iodone") error 5 numblks 64
Mar 27 13:58:18 srv-vln-des2 kernel: XFS (dm-4): xfs_do_force_shutdown(0x2)
called from line 1170 of file fs/xfs/xfs_log.c.  Return address =
0xffffffffa012a4c1
Mar 27 13:58:18 srv-vln-des2 kernel: XFS (dm-4): Log I/O Error Detected.
Shutting down filesystem
Mar 27 13:58:18 srv-vln-des2 kernel: XFS (dm-4): Please umount the
filesystem and rectify the problem(s)
Mar 27 13:58:18 srv-vln-des2 kernel: attempt to access beyond end of device
Mar 27 13:58:18 srv-vln-des2 kernel: dm-0: rw=0, want=562056, limit=24576
Mar 27 13:58:18 srv-vln-des2 kernel: device-mapper: thin:
process_bio_read_only: dm_thin_find_block() failed: error = -5
Mar 27 13:58:18 srv-vln-des2 kernel: XFS (dm-4): metadata I/O error: block
0x6804bc ("xlog_iodone") error 5 numblks 64
Mar 27 13:58:18 srv-vln-des2 kernel: XFS (dm-4): xfs_do_force_shutdown(0x2)
called from line 1170 of file fs/xfs/xfs_log.c.  Return address =
0xffffffffa012a4c1
Mar 27 13:58:18 srv-vln-des2 kernel: attempt to access beyond end of device
Mar 27 13:58:18 srv-vln-des2 kernel: XFS (dm-4): xfs_log_force: error 5
returned.
Mar 27 13:58:18 srv-vln-des2 kernel: dm-0: rw=0, want=562056, limit=24576
Mar 27 13:58:18 srv-vln-des2 kernel: device-mapper: thin:
process_bio_read_only: dm_thin_find_block() failed: error = -5
Mar 27 13:58:18 srv-vln-des2 kernel: attempt to access beyond end of device
Mar 27 13:58:18 srv-vln-des2 kernel: dm-0: rw=0, want=562056, limit=24576
Mar 27 13:58:18 srv-vln-des2 kernel: device-mapper: thin:
process_bio_read_only: dm_thin_find_block() failed: error = -5
Mar 27 13:58:18 srv-vln-des2 kernel: attempt to access beyond end of device
Mar 27 13:58:18 srv-vln-des2 kernel: dm-0: rw=0, want=562056, limit=24576
Mar 27 13:58:18 srv-vln-des2 kernel: device-mapper: thin:
process_bio_read_only: dm_thin_find_block() failed: error = -5
Mar 27 13:58:18 srv-vln-des2 kernel: XFS (dm-4): metadata I/O error: block
0x6804fc ("xlog_iodone") error 5 numblks 64
Mar 27 13:58:18 srv-vln-des2 kernel: XFS (dm-4): xfs_do_force_shutdown(0x2)
called from line 1170 of file fs/xfs/xfs_log.c.  Return address =
0xffffffffa012a4c



After that, gluster was shutdown and with it the 2 server are shtudown too.
The lvm partition was missing and so far I haven't been able restore the
file system. All data is missing??
I don't understand the situation and I don't know if it's due a xfs
filesystem or glusterfs fail. Someone it has been this situation?

Thanks.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://www.gluster.org/pipermail/gluster-users/attachments/20150331/9858bd68/attachment.html>