Hi all,
Been reading this thread with interest the last few weeks and was wondering the feasibility of this type of cluster for the storage of my VM servers. I have a mix of vSphere / ESX servers with Hyper-V and Xen on our network that I'd like to build a fault
tolerent storage solution. Based on the comments on this thread I've been toying with a few ideas...
Attached is a rough outline of what I'm considering putting together. The top layer will be servers with the actual disks. I'm looking at the Areca 1880 RAID card series to build a few 8 disk RAID6 in each node. Those nodes will then pass their RAIDed
arrays (sda) to the mid level iSCSI targets (head nodes) which will use cLVM w/ Mirroring to build Volume Groups across the two disk servers. They would have their own IP addresses to be used as targets by the VM servers which would use MPIO to multipath between
the two head nodes. The VM servers would handle the filesystems. Does this make sense / seem feasible? I'm trying to eliminate as many single points of failure as possible. I believe this solution would allow for failure at each level without any interruption
in service, but will also allow all disks to contribute to the performance of the entire pool.
Thanks,
Ryan
