On Tue, Oct 28, 2014 at 9:53 PM, Lindsay Mathieson <lindsay.mathieson@xxxxxxxxx> wrote: > Ok, thanks James, Juan. > > Given my budget, I think I'll switch to using a single 3TB drive in > each node, but add an extra 1GB Intel network card to each node and > bond them for better network performance. Did you test your workload to find your bottlenecks, or is this all just conjecture? Test! > > Also I will be adding a third proxmox node for quorum purposes - it > will just be a Intel NUC, won't be used for running VM's (though it > could manage a couple). Sweet... I almost bought a NUC to replace my Pentium 4 home server, but they were kind of pricey. How is it? > > > On 29 October 2014 11:10, Juan José Pavlik Salles <jjpavlik@xxxxxxxxx> wrote: >> RAID6 is the best choice when working with arrays with many disks. RAID10 >> doesn't make sense to me since you already have replication with gluster. Keep in mind that if you've got an array of 24 disks, you'd probably want to split that up into multiple RAID 6's. IOW, you'll have a few bricks per host, each composed of a RAID 6. I think the magic number of disks for a set is probably at least six, but not much more than eight. I got this number from my imagination. Test your workloads (also under failure scenarios) to decide for yourself. Cheers, James _______________________________________________ Gluster-users mailing list Gluster-users@xxxxxxxxxxx http://supercolony.gluster.org/mailman/listinfo/gluster-users
