Sagar Borikar wrote:
> Sagar Borikar wrote:
>> Copy is of the same file to 30 different directories and it is
>> Here is the setup:
>> It's a JBOD with Volume size 20 GB. The directories are empty and this
>> is basically continuous copy of the file on all thirty directories.
>> surprisingly none of the copy succeeds. All the copy processes are in
>> Uninterruptible sleep state and xfs_repair log I have already attached
>> With the prep. As mentioned it is with 2.6.24 Fedora kernel.
> It would probably be best to try a 2.6.26 kernel from rawhide to be sure
> you're closest to the bleeding edge.
> <Sagar> Sure Eric but I reran the test and I got similar errors with
> 2.6.24 kernel on x86. I am still confused with the results that I see on
> 2.6.24 kernel on x86 machine. I see that the used size shown by ls is
> way too huge than the actual size. Here is the log of the system
> [root@lab00 ~/test_partition]# ls -lSah
> total 202M
> -rw-r--r-- 1 root root 202M Jul 4 14:06 original ---> this I sthe file
> Which I copy.
> drwxr-x--- 65 root root 12K Jul 6 21:57 ..
> -rwxr-xr-x 1 root root 189 Jul 4 16:31 runall
> -rwxr-xr-x 1 root root 50 Jul 4 16:32 copy
> drwxr-xr-x 2 root root 45 Jul 6 22:07 .
It'd be great if you provided these actual scripts so we don't have to
guess at what you're doing or work backwards from the repair output :)
> dmesg log doesn't give any information. Here is XFS related
> XFS mounting filesystem loop0
> Ending clean XFS mount for filesystem: loop0
> Which is basically for mounting XFS cleanly. But there is no exception
> in XFS.
and nothing else of interest either?
> Filesystem has become completely sluggish and response time is increased
> 3-4 minutes for every command. Not a single copy is complete and all
> the copy processes are sleeping continuously.
And how did you recover from this; did you power-cycle the box?