Re: [Gluster-devel] unify translator & namespac

[Basavanagowda Kanur]

Martin,
  Replies in-line.

On Tue, Mar 18, 2008 at 11:15 AM, Martin Fick <address@hidden> wrote:

> --- "Amar S. Tumballi" <address@hidden> wrote:
> > Hence we came up with a namespace design, which
> > will not contain any critical data, and also it
> > can rebuild from scratch if you choose to use
> > different new namespace after a while.
>
> Silly, question, does that mean that the namespace can
> be destroyed between mounts?  If yes, would it mean
> that it gets rebuilt on each mount or would it
> be filled lazily?


Yes, you can destroy namespace between mounts.  Unify rebuilds namespaces on
each mount, if it finds inconsistancies. Namespace will not be rebuilt at
one shot, it is rebuilt on demand.


>
> > About your question, whether its mandatory to use
> > namespace, YES it is. If you don't give this
> > option, you will not be able to mount GlusterFS
> > filesystem.
>
> It seems like it would be neat to be able to use the
> schedulers from the unify translator without a
> namespace to get the ability to do load balancing on
> across AFRed backend servers.  I know that AFR load
> balancing is on the roadmap, but since the schedulers
> offer a nice variety of algorithms, I was wondering if
> using the unify translators wouldn't already work (or
> be close to working) without actually doing
> unification?
>
> -Martin
>
>
>
>
>  
> ____________________________________________________________________________________
> Looking for last minute shopping deals?
> Find them fast with Yahoo! Search.
> http://tools.search.yahoo.com/newsearch/category.php?category=shopping
>
>
>
> _______________________________________________
> Gluster-devel mailing list
> address@hidden
> http://lists.nongnu.org/mailman/listinfo/gluster-devel
>



-- 
Life has always given me what i needed, but never gave me what i wanted.