I have been a long time Gluster fan however I gave up on it about a year ago when it just was not working out for xen, so I moved to NetApp. I now am looking at offering storage as a service and NetApp just can't scale or offer the price point needed. I would love to hear feedback from users who are running large amounts of data on GlusterFS. I want to scale to hundreds of notes, but starting small at first. Looking at 5 cites with the following: 8 servers: Dual Xeon X5680 3.3 GHz 3Ware 9750-8i 6 Gb/s 32 2TB drives RAID 6 + hot spare Mellanox MHGS18 10 Gb/s Infiniband Each server will have raw 60 TB of space and two servers will be unified together for redundancy. Pairs of servers will be distributed into one 240 TB volume in each city. The plan needs to scale to 4 PB in each within 1 year.><>Nathan Stratton CTO, BlinkMind, Inc. nathan at robotics.net nathan at blinkmind.com robotics.net blinkmind.com
Not to go off topic too much but what was your problem with gluster and xen? I'm preparing to roll out a rather large xen based product and utilize gluster to store the sparse image files for each instance. Haven't ran into many issues yet, so I'm just wondering if you know something I don't :) ----- Original Message ----- From: gluster-users-bounces at gluster.org <gluster-users-bounces at gluster.org> To: Gluster-users at gluster.org <Gluster-users at gluster.org> Sent: Sat Jul 03 11:37:12 2010 Subject: [Gluster-users] Gluster I have been a long time Gluster fan however I gave up on it about a year ago when it just was not working out for xen, so I moved to NetApp. I now am looking at offering storage as a service and NetApp just can't scale or offer the price point needed. I would love to hear feedback from users who are running large amounts of data on GlusterFS. I want to scale to hundreds of notes, but starting small at first. Looking at 5 cites with the following: 8 servers: Dual Xeon X5680 3.3 GHz 3Ware 9750-8i 6 Gb/s 32 2TB drives RAID 6 + hot spare Mellanox MHGS18 10 Gb/s Infiniband Each server will have raw 60 TB of space and two servers will be unified together for redundancy. Pairs of servers will be distributed into one 240 TB volume in each city. The plan needs to scale to 4 PB in each within 1 year.><>Nathan Stratton CTO, BlinkMind, Inc. nathan at robotics.net nathan at blinkmind.com robotics.net blinkmind.com _______________________________________________ Gluster-users mailing list Gluster-users at gluster.org gluster.org/cgi-bin/mailman/listinfo/gluster-users
What did you end up using instead? ----- Original Message ----- From: gluster-users-bounces at gluster.org <gluster-users-bounces at gluster.org> To: Gluster General Discussion List <gluster-users at gluster.org> Sent: Sat Jul 03 12:34:32 2010 Subject: Re: [Gluster-users] Gluster On Sat, 3 Jul 2010, Andy Pace wrote:> Not to go off topic too much but what was your problem with gluster and xen? > > I'm preparing to roll out a rather large xen based product and utilize gluster to store the sparse image files for each instance. > > Haven't ran into many issues yet, so I'm just wondering if you know something I don't :)Bad bad bad news... The biggest issue may be fixed now, but once a xen file was opened Gluster would only write to one node. A smaller issue is you have to use file rather then tap:aio and file is biggest and can cause corruption in xen. There was one other issue, but don't remember what it was right now.><>Nathan Stratton CTO, BlinkMind, Inc. nathan at robotics.net nathan at blinkmind.com robotics.net blinkmind.com _______________________________________________ Gluster-users mailing list Gluster-users at gluster.org gluster.org/cgi-bin/mailman/listinfo/gluster-users