[Users] A question about Node RAM

[Tim Small]

On 07/01/12 08:33, Kirill Korotaev wrote:
> > (maybe pacemaker with drbd, or glusterfs, or sheepdog) to distribute the storage between the nodes, and allow moving VMs between nodes.
>   
> do not recomment gluster or sheepdog - they are nowhere near production quality. So speaking about reliability - a described HW with SAS drives RAID is by far more reliable.
>   

I've not done much with gluster, but I know people who have it in
production and are happy with it.  Sheepdog looks very promising - we've
had a bit of a play with it and plan to do more investigation in the
future...  We have drbd in production and are happy with it.

Over the years, I've had so much trouble with hardware RAID, that I now
avoid it if at all possible.

My experience with real top-end hardware has been that you get to find
lots of interesting new bugs (both software and hardware) because you're
using relatively unusual hardware - you end up with a machine which is
like 0.01% of the global machines running Linux instead of 5% or
whatever.  When you do hit such bugs, often the developers can't
reproduce the issue because they don't have access to the same hardware...

RAISe - Rudundant Array of Inexpensive Servers!  :-)

Tim.

-- 
South East Open Source Solutions Limited
Registered in England and Wales with company number 06134732.  
Registered Office: 2 Powell Gardens, Redhill, Surrey, RH1 1TQ
VAT number: 900 6633 53  http://seoss.co.uk/ +44-(0)1273-808309