[Gluster-users] Ubuntu GlusterFS in Production

Dan Mons dmons at cuttingedge.com.au
Thu Dec 5 21:57:34 UTC 2013


I'm running 6x 37TB Gluster nodes in distribute-replicate with
software bonded 10GbE NICs (using Mode 2 balance-xor) per cluster, on
4 clusters (24 nodes all up across 2 sites).

With 10GbE NICs, we don't see much speed boost out of the bonding, but
there's a good per-client latency drop when network traffic gets busy.

CentOS6 on the Gluster nodes, Kubuntu 12.04 on Linux clients (along
with some Mac and Windows boxes in the mix).

-Dan
----------------
Dan Mons
R&D SysAdmin
Unbreaker of broken things
Cutting Edge
http://cuttingedge.com.au


On 6 December 2013 06:16, Nux! <nux at li.nux.ro> wrote:
> On 05.12.2013 19:07, Josh Boon wrote:
>>
>> We're using it in production too. We're on KVM 1.6, gluster 3.4.1
>> running on Ubuntu 13.04.  No problems but do be aware that you'll want
>> fast links if you actually want to saturate your disk bandwidth. We've
>> bonded 10gbps links and we still saturate those before we fully
>> utilize our IO. I've not tested NFS specifically but performance is
>> something you're looking for I'd strongly suggest gfapi which gets us
>> near 400MBps writes in a replica 2 config across the above mentioned
>> interfaces.  You'll have to do some work on the KVM sources for gfapi
>> though as it's not even made it into the debian unstable packages.
>
>
> Not really, RHEL/CENTOS 6.5 has KVM which can use gfapi.
> https://access.redhat.com/site/documentation/en-US/Red_Hat_Enterprise_Linux/6/html-single/6.5_Release_Notes/index.html#sect-kvm
>
> --
> Sent from the Delta quadrant using Borg technology!
>
> Nux!
> www.nux.ro
>
> _______________________________________________
> Gluster-users mailing list
> Gluster-users at gluster.org
> http://supercolony.gluster.org/mailman/listinfo/gluster-users



More information about the Gluster-users mailing list