[xfs-masters] [Bug 783] New: xfs_inotobp: xfs_imap() returned an error 22 on sdc. Returning error.

[bugzilla-daemon@xxxxxxxxxxx]

http://oss.sgi.com/bugzilla/show_bug.cgi?id=783

           Summary: xfs_inotobp: xfs_imap()  returned an error 22 on sdc.
                    Returning error.
           Product: Linux XFS
           Version: unspecified
          Platform: PC
        OS/Version: Linux
            Status: NEW
          Severity: critical
          Priority: P2
         Component: XFS kernel code
        AssignedTo: xfs-master@xxxxxxxxxxx
        ReportedBy: magnard@xxxxxx


Hello,

This machine (2 8-cores opterons, Tyan S2932 mother board, 32GB of RAM) has two
3ware 9650SE-8LPML RAID controlers, both used as RAID5.
One of those 2 RAID partition of 5TB, upon active disk access, shows I/O error
very often (typically after a few hours of use), and gets unusable (I/O error
upon access), although the other one works without a glitch.
Here are the logs:

Jun  9 11:04:33 cosmix5 [3986204.452552] xfs_inotobp: xfs_imap()  returned an
error 22 on sdc.  Returning error.
Jun  9 11:04:33 cosmix5 [3986204.452561] xfs_iunlink_remove: xfs_inotobp() 
returned an error 22 on sdc.  Returning error.
Jun  9 11:04:33 cosmix5 [3986204.452565] xfs_inactive:  xfs_ifree() returned an
error = 22 on sdc
Jun  9 11:04:33 cosmix5 [3986204.452570] xfs_force_shutdown(sdc,0x1) called from
line 1819 of file fs/xfs/xfs_vnodeops.c.  Return address = 0xffffffff811dde6e
Jun  9 11:04:33 cosmix5 [3986204.452583] Filesystem "sdc": I/O Error Detected. 
Shutting down filesystem: sdc
Jun  9 11:04:33 cosmix5 [3986204.452586] Please umount the filesystem, and
rectify the problem(s)
Jun  9 11:04:33 cosmix5 [3986204.452612] xfs_iunlink_remove:
xfs_trans_read_buf()  returned an error 5 on sdc.  Returning error.

I am able to umount/remount the partition without problem or apparent data loss
(no lost+found directory created).
The RAID5 array is OK (no failed disk).
I do not know how to get xfs version on this kernel, but it's a 2.6.23-gentoo-r9
kernel from gentoo (cf. http://gentoo-portage.com/sys-kernel/gentoo-sources )
with this patch applied (for buggy B2 opteron):
https://www.x86-64.org/pipermail/discuss/2007-December/010260.html

# xfs_info  /data/cosmix5raid2
meta-data=/dev/sdc               isize=256    agcount=32, agsize=40053728 blks
         =                       sectsz=512   attr=0
data     =                       bsize=4096   blocks=1281719040, imaxpct=25
         =                       sunit=16     swidth=128 blks, unwritten=1
naming   =version 2              bsize=4096  
log      =internal               bsize=4096   blocks=32768, version=1
         =                       sectsz=512   sunit=0 blks
realtime =none                   extsz=65536  blocks=0, rtextents=0

This problem makes those 5TB of disk almost unusable.
I have not yet been able to reproduce on purpose this bug, but it occurs quite
quickly on disk usage.
I found some similar error-messages in previous bugs, but with 2.4 kernel.
I am thinking about upgrading to a newer kernel version, but the AMD kernel
patch should only be applied to 2.6.23... So I'd appreciate any help !

Thanks,
Cheers,
Frédéric Magnard.

-- 
Configure bugmail: http://oss.sgi.com/bugzilla/userprefs.cgi?tab=email
------- You are receiving this mail because: -------
You are the assignee for the bug, or are watching the assignee.