Adding Gluster users' mail list.

On Apr 5, 2019 06:02, Leo David <leoalex@gmail.com> wrote:

Hi Everyone,

Any thoughts on this ?

On Wed, Apr 3, 2019, 17:02 Leo David <leoalex@gmail.com> wrote:

Hi Everyone,

For a hyperconverged setup started with 3 nodes and going up in time up to 12 nodes, I have to choose between LSI2008 ( jbod ) and LSI9265 (raid).

Perc h710 ( raid ) might be an option too, but on a different chassis.

There will not be many disk installed on each node, so the replication will be replica 3 replicated-distribute volumes across the nodes as:

node1/disk1  node2/disk1  node3/disk1

node1/disk2  node2/disk2  node3/disk2

and so on...
As i will add nodes to the cluster ,  I intend expand the volumes using the same rule.

What would it be a better way,  to used jbod cards ( no cache ) or raid card and create raid0 arrays ( one for each disk ) and therefore have a bit of raid cache ( 512Mb ) ?

Is raid caching a benefit to have it underneath ovirt/gluster as long as I go for "Jbod"  installation anyway ?

Thank you very much !
--

Best regards, Leo David