[Gluster-users] gluster 3.2.0 - totally broken?
udo.waechter at uni-osnabrueck.de
Wed May 18 19:09:59 UTC 2011
On 18.05.2011, at 19:14, Anand Avati wrote:
> Do you know what kind of access was performed on those files? Were they just copied in (via cp), were they rsync'ed over an existing set of data? Was it data carried over from 3.1 into a 3.2 system? We hate to lose
We started our first experiments (and quickly after gone into production) with our cloud infrastructure.
There, the use case is pretty easy:
one user and a shared (distributed) volume for >30 VMs. This worked pretty well pretty quick and we started using it in production. For months everything was great and still is.
The second use case was then to create a distributed+replicated volume for the user data.
No problem so far.
* then we rsynced the data from our old nfs-servers to the new volume
* We moved files and directories around within the volume
* We changed access permissions on those files. Basically going to 0700 for user's personal directories, and to 0750 for working group-directories. The latter also are "g+s" to retain groups over edits/removes/creates of files/directories. These directories are giving us the problems described. There are duplicate files, vanishing files and such. All of these described in my previous posts. All the groups are secondary groups of the users.
Last week we got productive with this volume and as soon as people started working all these problems turned up. The bad part is, that they become worse with every day.
The most recent development is, that even in those directories that are owned by a single user and its primary group these problems turn up. Its so bad, that those people even can't create new files.
> users (community users or paid customers equally) and will do our best to keep you happy. Please file a bug report with as much history as possible and we will have it assigned on priority.
I already mentioned the bugs that seem to describe the same problems. I really do not think that creating new ones describing the same problems would help. Maybe the old ones should be reopened. These bugs mentioned in: http://gluster.org/pipermail/gluster-users/2011-May/007619.html are basically the same.
Currently I really do not know how to describe/analyze the problem further.
Unfortunatly I need to come up with a solution ASAP. Our institute is a pretty busy one, currently there are a lot of experiments going on. Returning to the old servers is not really an option. We do not have the free space to accomodate all the data.
---[ Institute of Cognitive Science @ University of Osnabrueck
---[ Albrechtstrasse 28, D-49076 Osnabrueck, 969-3362
---[ Documentation: https://doc.ikw.uni-osnabrueck.de
-------------- next part --------------
A non-text attachment was scrubbed...
Size: 2427 bytes
Desc: not available
More information about the Gluster-users