[Gluster-users] Why does NUFA not allow mounts even from trusted peers without a subvolume?

[Anand Avati]

Oops, you are right. I got misled by git-describe. Can you please add
http://review.gluster.org/5414/ to the backport wishlist (for 3.4.2) -
http://www.gluster.org/community/documentation/index.php/Backport_Wishlist

Thanks!
Avati


On Wed, Dec 4, 2013 at 2:34 PM, Michael Lampe <mlampe0 at googlemail.com>wrote:

> Just checked nufa.c from the official 3.4.1 sources and things look very
> much different from
>
> http://review.gluster.org/#/c/5414/2/xlators/cluster/dht/src/nufa.c
>
> There is surely no such fallback.
>
> -Michael
>
>
> Michael Lampe wrote:
>
>> I'm using the 3.4.1-3.el5 packages from gluster.org.
>>
>> Am I perhaps misinterpreting the problem?
>>
>> -Michael
>>
>> Anand Avati wrote:
>>
>>> You are probably using 3.3 or older? This has been fixed in 3.4 (
>>> http://review.gluster.org/5414)
>>>
>>> Thanks,
>>> Avati
>>>
>>>
>>> On Wed, Dec 4, 2013 at 2:05 PM, Michael Lampe
>>> <mlampe0 at googlemail.com>wrote:
>>>
>>>  I've installed GlusterFS on our 23-node Beowulf cluster. Each node has a
>>>> disc which provides a brick for the GlusterFS volume and every node
>>>> mounts
>>>> this volume. The NUFA translator is ideal for the code we run and
>>>> everythings works fine so far.
>>>>
>>>> Only problem is the frontend node, which does not have a subvolume:
>>>> After
>>>> I've turned on NUFA, it no longer can mount the volume. :(
>>>>
>>>> [2013-12-04 21:35:44.262738] E [nufa.c:641:init] 0-gv0-dht: Could not
>>>> find
>>>> specified or local subvol
>>>> [2013-12-04 21:35:44.262766] E [xlator.c:390:xlator_init] 0-gv0-dht:
>>>> Initialization of volume 'gv0-dht' failed, review your volfile again
>>>> [2013-12-04 21:35:44.262783] E [graph.c:292:glusterfs_graph_init]
>>>> 0-gv0-dht: initializing translator failed
>>>> [2013-12-04 21:35:44.262799] E [graph.c:479:glusterfs_graph_activate]
>>>> 0-graph: init failed
>>>>
>>>> Is there any technical reason for treating things this way? Why cannot
>>>> NUFA fall back to distribute, like it does when the local subvolume
>>>> has not
>>>> enough free space?
>>>>
>>>> Or is there a better way to include a frontend node?
>>>>
>>>> -Michael
>>>> _______________________________________________
>>>> Gluster-users mailing list
>>>> Gluster-users at gluster.org
>>>> http://supercolony.gluster.org/mailman/listinfo/gluster-users
>>>>
>>>>
>>>
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://supercolony.gluster.org/pipermail/gluster-users/attachments/20131204/f37b2bac/attachment.html>