[Gluster-users] [Users] Creation of preallocated disk with Gluster replication

Karli Sjöberg Karli.Sjoberg at slu.se
Thu Jan 9 07:35:46 UTC 2014


On Wed, 2014-01-08 at 16:05 -0600, Darrell Budic wrote:
> On Jan 8, 2014, at 3:29 PM, Karli Sjöberg <Karli.Sjoberg at slu.se> wrote:
> 
> > 
> > 
> > Skickat från min iPhone
> > 
> >> 8 jan 2014 kl. 19:11 skrev "Darrell Budic" <darrell.budic at zenfire.com>:
> >> 
> >> 
> >>> On Jan 8, 2014, at 11:55 AM, Karli Sjöberg <Karli.Sjoberg at slu.se> wrote:
> >>> 
> >>> 
> >>> 
> >>> Skickat från min iPhone
> >>> 
> >>>> 8 jan 2014 kl. 18:47 skrev "Darrell Budic" <darrell.budic at zenfire.com>:
> >>>> 
> >>>> Grégoire-
> >>>> 
> >>>> My test setup, running a version of the nightly self-hosted setup w/ gluster distributed/replicated disks as shared storage, in a NFS cluster:
> >>>> 
> >>>> Core i5 3570K @ 3.4Ghz, 16G Ram
> >>>> Boot disks: 2x 32G SATA SSDs in raid-1
> >>>> Storage system: 4x500G Seagate RE3s in a ZFS raid-10 w/ 1GB ZIL & ~22G L2ARC caching from boot drives
> >>>> 1 1G ethernet
> >>>> 2 VMs running
> >>>> 
> >>>> Core2 Duo E8500 @ 3.16GHz, 8G Ram
> >>>> Boot disks: 2x 32G SATA SSDS in raid-1
> >>>> Storage system: 2x1500G WD Green drives in a  ZFS Raid w/ 1GB ZIL & ~22G L2ARC cache from boot drives
> >>>> 1 1G ethernet
> >>> 
> >>> Just curious, are you doing ZFS in Linux?
> >>> 
> >>> /K
> >> 
> >> Yes, forgot to mention those are freshly built Centos 6.5 systems with zfs 0.6.2, and glusterfs-3.4.1-3.el6.x86_64, vdsm-gluster-4.13.2-1.el6.noarch for testing/experimenting. Bought some cheap SSDs and just grabbed systems and platters I had around for it. Testbedding and getting some experience with the self hosted engine, since I’d like to move to it once it’s released. Also looking forward to testing native gluster on this setup.
> >> 
> >> I have a production ovirt cluster with a linux zfs based NFS storage server, the backend has been very stable since I got rid of Nextenta and went to linux. Sounds odd, I know, but couldn’t get good support for a community nextenta server I inherited. I was having driver level box lockup issues with openSolaris that I couldn’t resolve. So I rebuilt it with linux, imported the pool, and haven’t looked back or had a storage failure since.
> >> 
> >> -Darrell
> >> 
> > 
> > Glad to hear you got it working, inheritance is a *****:) Never considered joining the daemon side of the force (FreeBSD) ? Oh, and are you running it native with ZoL or through FUSE?
> > 
> > /K
> 
> Native ZoL, it’s just a big fat 10g NFS server for the host nodes. It’s been solid since Ovirt 3.1 or so. Been using linux (old Slackware hand here) too long to turn back to the daemon side ;) I use macs and OS X for the desktop to get my mach Kernel bsd-ish fix, so the even darker side? :)
> 
>   -Darrell

Funny, I used to be a Slacker as well, before I met BSD:) The leap is
actually quite small, which probably isn´t that surprising since Slack
is (or at least was, last time I worked with it) supposed to be the
closest to Unix you get, while running Linux:)

/K


More information about the Gluster-users mailing list