I faced similar issues with git checkout on RHS 3. I didn't debug it further, or check if it is fixed in a recent update, but it sounds like a similar issue since git checkout would also do a lot of renaming. Can you try doing a git checkout to confirm if it's the same issue ? I am also using it with no root squash for now.
On Mon, Jul 4, 2016 at 6:44 AM, Matt Robinson <m.robinson@xxxxxxxxxxxxxxx> wrote:
Hi,
I'm fairly new to gluster so please forgive me if I'm in any way out of protocol for this list.
I have a distributed volume with 2 servers hosting bricks and a third just managing the system.
I really want root squashing, as there are a large number of clients and I do not want a bad keystroke on one to wipe out the contents of the gluster file-system.
I'm using gluster 3.7.10 on Scientific Linux 6.7.
I just cannot get gluster to work properly for normal users with root-squashing enabled. The problem is easiest to reproduce if one creates a directory with mkdir, creates a file with say 'echo hi > filename' and then tries to rename the latter to place it in the former using mv. This fails about 50% of the time. My reading suggests that it occurs when gluster decides to move the file from one brick to another as it renames it. rebalance and fix-layout have been run, but have long finished and the problem persists.
I've spent a fair amount of time googling this issue and it's clearly not unprecedented, but it's supposedly fixed long before v3.7.10.
I really would appreciate it if somebody could rescue me. For the moment I'm running with server.root-squash turned off.
Thanks,
Matt.
_______________________________________________
Gluster-users mailing list
Gluster-users@xxxxxxxxxxx
http://www.gluster.org/mailman/listinfo/gluster-users
_______________________________________________ Gluster-users mailing list Gluster-users@xxxxxxxxxxx http://www.gluster.org/mailman/listinfo/gluster-users
