[Gluster-users] GlusterFS absolute max. storage size in total?

[Mohamed Pakkeer]

Hi Amar,

Currently, we are running 40 node cluster and each node has
36*6TB(210TB).As of now we don't face any issue with read and write
performance  except folder listing and disk failure healing. Planning to
start another cluster with 36*10TB(360)per node. What kind of problem will
we face if we go with 36*10(360)per node. Planned 360TB per node is far
from recommended 64TB. We are using Glusterfs with disperse volume for
video archival.

Regards
K. Mohamed Pakkeer

On 20-Apr-2017 9:00 AM, "Amar Tumballi" <atumball at redhat.com> wrote:

>
> On Wed, 19 Apr 2017 at 11:07 PM, Peter B. <pb at das-werkstatt.com> wrote:
>
>> Hello,
>>
>> Could you tell me what the technically maximum limit of capacity of a
>> GlusterFS storage is?
>> I cannot find any official statement on this...
>>
>> Somewhere it says "several Petabytes", but that's a bit vague.
>
>
> It is mostly vague because the total storage depends on 2 things, what is
> per node storage you can get, and then how many nodes you have in cluster?
>
> It is scalable comfortably for 128nodes, and per node you can have 64TB
> drives, making it 8PB.
>
>
>
>> I'd need it for arguing pro GlusterFS in comparison to other systems.
>
>
> Hope the above info helps you. Btw, we are targeting more scalability
> related improvements in Gluster 4.0, so it should be much larger number
> from next year.
>
> -Amar
>
>
>
>>
>> Thank you very much in advance,
>> Peter B.
>>
>> _______________________________________________
>> Gluster-users mailing list
>> Gluster-users at gluster.org
>> http://lists.gluster.org/mailman/listinfo/gluster-users
>>
> --
> Amar Tumballi (amarts)
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://lists.gluster.org/mailman/listinfo/gluster-users
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.gluster.org/pipermail/gluster-users/attachments/20170420/fd2844c7/attachment.html>