[Gluster-users] Self Heal Performance

[Lindsay Mathieson]

How granular is glusterfs self heal with large vm images?
(30GB-100GB). Some of the commentary I saw online seemed to think it
was very slow and inefficient, implying that self heal involved
resyncing entire files, rather than blocks.

So, if in a replicated setup, a node goes down for a while, but the
VM's keep running and writing to their image on the other nodes.

What happens when the node comes back up? does it have to recopy the
entire image from the other nodes or is it just the writes since it
was down that have to be replicated?

thanks,

-- 
Lindsay