glusterd_get_brick_mount_dir () does a brick_dir++  which seems to cause
this problem and removing this line fixes the problem. Commit f846e54b
introduced it.

Ccing Avra/Rajesh

mount_dir is used by snapshot, however I am just wondering how are we
surviving this case.

~Atin

On Thu, Aug 4, 2016 at 5:39 PM, Milind Changire <[email protected]> wrote:

> here's one of the brick definition files for a volume named "twoXtwo"
>
> [root@f24node0 bricks]# cat f24node1\:-glustervols-twoXtwo-dir
> hostname=f24node1
> path=/glustervols/twoXtwo/dir
> real_path=/glustervols/twoXtwo/dir
> listen-port=0
> rdma.listen-port=0
> decommissioned=0
> brick-id=twoXtwo-client-1
> mount_dir=/lustervols/twoXtwo/dir          <-- shouldn't the value be
>                                                /glustervols/...
>                                                there's a missing 'g'
>                                                after the first '/'
> snap-status=0
>
>
> This *should* happen for all volumes and for all such brick definition
> files or whatever they are called.
> BTW, I'm working with the upstream mainline sources, if that helps.
>
> I'm running a 2x2 distribute-replicate volume.
> 4 nodes with 1 brick per node.
> 1 brick for the hot tier for tiering.
>
> As far as I can tell, I haven't done anything fancy with the setup.
> And I have confirmed that there is no directory named '/lustervols'
> on any of my cluster nodes.
>
> --
> Milind
> _______________________________________________
> Gluster-devel mailing list
> [email protected]
> http://www.gluster.org/mailman/listinfo/gluster-devel
>



-- 

--Atin
_______________________________________________
Gluster-devel mailing list
[email protected]
http://www.gluster.org/mailman/listinfo/gluster-devel

Reply via email to