On Fri, Sep 24, 2010 at 04:07:23PM +0200, Turbo Fredriksson wrote:
| I started with a few hundred gig on my FS
| (on top of LVM which in turn is on top a bunch
| of MD devices).
|
| Slowly increasing the size with pvmove/{vg,lv}extend
| etc. Yesterday, I added more disks yet again and
| now have about 8Tb on one FS... ~1Tb free. But still
| get the 'No space left on device'.
|
|
| I've been looking through the 'Net and it
| must be because I'm out of inodes (and that
| the data is on the first 1Tb etc)...
You may may be able to workaround the the problem by increasing imaxpct
on the filesystem.
See http://oss.sgi.com/archives/xfs/2010-09/msg00295.html
| I'm running on AMD 64bit (native kernel, but
| Debian Lenny 32bit userland - 2.6.2[4-6] kernel).
|
|
|
| Now, if I use (I'll try to upgrade to a newer
| kernel so I can reverse) the inode64, what
| impact will this have? I guess I still have
| to move my firstly created 1Tb of-disk and
| then back again?
|
|
| The worst thing is that every time I grow
| the FS, I have to reboot into a 32bit kernel:
|
| xfs_growfs: XFS_IOC_FSGROWFSDATA xfsctl failed: Invalid argument
This may be becuase your are running 32bit userland.
| and then back to the 64bit kernel... How will
| this (system/FS) react if I go 64bit inodes?!
|
|
| And how safe is this!? I just don't have the
| possibility to do a full backup of all this
| data, not even temporarily... I _might_ be
| able to do this in a few weeks (work is ordering
| a bunch of LaCie 8Tb USB/eSATA storage boxes
| which I might be able to load for a few days
| 'to do some stress testing on' :)
|
|
| References:
| http://xfs.org/index.php/XFS_FAQ#Q:_Why_do_I_receive_No_space_left_on_device_after_xfs_growfs.3F
| http://xfs.org/index.php/XFS_FAQ#Q:_Can_I_just_try_the_inode64_option_to_see_if_it_helps_me.3F
| http://www.doc.ic.ac.uk/~dcw/xfs_16tb/
Once you have 64bit inodes, it is difficult to go back to 32bit inodes.
The filesystem will stay together, but you may not be able to access
your files with 64bit inodes from 32bit applications.
--
Geoffrey Wehrman
_______________________________________________
xfs mailing list
xfs@xxxxxxxxxxx
http://oss.sgi.com/mailman/listinfo/xfs
