We have an ML350 G6 running VMware 5.x with a single datastore - two virtual machines, both Win2008 servers - one a DC/filer server and the other a low-use SQL 2008 server.
The server had 4x300GB SAS 10K drives configured in a RAID 5 on the internal SmartArray P410i/256MB controller.
An urgent, unexpected need came up for more storage space so we added 4 more 300GB 10K SAS drives, configured them for RAID5 again on the same controller (we couldn't afford the space for anything other than RAID5) and SPANNED the datastore across this new LUN.
It seems that, more times than not, throughput - especially during backups - is especially hampered. Average latency is HIGH - approaching 45 ms sometimes. We're experiencing problems the VMs becoming unresponsive when consolidating snapshots after backups, etc.
My question is - would it make sense to (after making sure I have good backups as verified by restoring to a temporary hypervisor) completely wipe the server (ESX is installed on the original RAID5 array), rebuild it as one RAID5 array across all 8 drives, then restore my VMs to it?
This would be a substantial effort on our part as there's more than 2.5 TB involved with the two VMs. Is it worth the effort to go from one datastore spanned across 2 RAID-5 arrays to a single RAID-5 array?