Hi Peter Robinson：
Thank you for your reply.
That's it,I used xfs as the underlying filesystem.
If the three postmark procresses run on one matchine，there been no this crash.
Does creating a same file in the same dir by different client of different matchines at the same time have any problme?
Thanks.
yours Jia Deming
2013-07-07
On Sun, Jul 7, 2013 at 7:12 PM, Peter Robinson <pbrobinson@xxxxxxxxx> wrote:
On Sun, Jul 7, 2013 at 12:06 PM, deming jia <jiademing.dd@xxxxxxxxx> wrote:What is the underlying filesystem that you use for the gluster brick?
> Hi,lists.
> I do a test in glusterfs-3.3.1,but have a crash，seems return an
> invalid indoe or invalid inode-table in stripe_lookup_cbk.
> The test likes this:
> 1. craate a dht+stripe volumes.
> 2.mount in three different machines
> 3.mkdir testdir in mount point
> 4.every machine start a postmark to craate a lot of little files
> named 1,2,3..... in testdir
>
> In short，three postmark process in three different machine create a
> lot of little files named 1,2,3,4..... in a same dir （testdir）
> use a dht+stripe volumes, this crash can be reproduce.
> In additionally，
> http://supercolony.gluster.org/pipermail/gluster-devel/2011-August/007441.html
> , it's decription is similar to my
> crash. How can I solve it？ Look forward to your reply,Thanks.
>
There's some known issues with ext4 that I'm not sure has been fixed
so it's recommended you use xfs as the underlying filesystem.
Peter
--
test mailing list
test@xxxxxxxxxxxxxxxxxxxxxxx
To unsubscribe:
https://admin.fedoraproject.org/mailman/listinfo/test
-- test mailing list test@xxxxxxxxxxxxxxxxxxxxxxx To unsubscribe: https://admin.fedoraproject.org/mailman/listinfo/test
