Gluster users - Dec 2015 - Arbiter vs Dummy Node Details

Hello All,

Forgive the duplicate but I forgot to give the first post a title so this
corrects that.  Anyway, I recently discovered the new arbiter functionality
of the 3.7 branch so I decided to give it a try.  First off, I too am
looking forward to the ability to add an arbiter to an already existing
volume as discussed in the following thread:
https://www.gluster.org/pipermail/gluster-users/2015-August/023030.html.

However, my first question for now is can someone perhaps go into a bit of
detail regarding the difference between using this new arbiter
functionality versus adding a dummy node with regards to helping to
eliminate split-brain?  In other words, a bit of information on which is
best and why?

Second, I noticed at the following URL where is discusses this new
functionality it says, and I quote "*By default, client quorum
(cluster.quorum-type) is set to auto . . ."* which I found to be a bit
confusing.  After setting up my new cluster I noticed that none of the
quorum settings including cluster.quorum-type seem to have a setting?

Arbiter Link
https://github.com/gluster/glusterfs/blob/release-3.7/doc/features/afr-arbiter-volumes.md

Thank you.
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://www.gluster.org/pipermail/gluster-users/attachments/20151229/804b85f1/attachment.html>

On 12/30/2015 04:20 AM, Kyle Harris wrote:
> Hello All,
>
> Forgive the duplicate but I forgot to give the first post a title so 
> this corrects that.  Anyway, I recently discovered the new arbiter 
> functionality of the 3.7 branch so I decided to give it a try.  First 
> off, I too am looking forward to the ability to add an arbiter to an 
> already existing volume as discussed in the following thread: 
> https://www.gluster.org/pipermail/gluster-users/2015-August/023030.html.
>
This is not implemented yet Kyle. We are targetting it for
3.8.
> However, my first question for now is can someone perhaps go into a 
> bit of detail regarding the difference between using this new arbiter 
> functionality versus adding a dummy node with regards to helping to 
> eliminate split-brain?  In other words, a bit of information on which 
> is best and why?
See this thread 
https://www.gluster.org/pipermail/gluster-users/2015-October/023915.html 
for more information. Client quorum is a better way to avoid split-brain 
of files.
Arbiter is a type of replicate volume which uses client quorum ( plus 
some arbitration logic)  to avoid split-brains.
>
> Second, I noticed at the following URL where is discusses this new 
> functionality it says, and I quote "/By default, client quorum 
> (cluster.quorum-type) is set to auto . . ."/ which I found to be a bit
> confusing. After setting up my new cluster I noticed that none of the 
> quorum settings including cluster.quorum-type seem to have a setting?
The client-quorum is indeed enabled and set to auto; it is just that the 
`volume info` output does not display it correctly.  It being fixed 
(http://review.gluster.org/#/c/11872/).

-Ravi
> /
> /
> Arbiter Link
>
https://github.com/gluster/glusterfs/blob/release-3.7/doc/features/afr-arbiter-volumes.md
>
> Thank you.
>
>
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://www.gluster.org/mailman/listinfo/gluster-users

-------------- next part --------------
An HTML attachment was scrubbed...
URL:
<http://www.gluster.org/pipermail/gluster-users/attachments/20151230/6e9b669c/attachment.html>