>
>
> So, when you combine ZFS with the power to extend it with these two
> methods you _should_ have the ultimate small, random IO solution.  ....
> should.
>

sweet ...

what happens though:

1.  When you grow out of physical storage capacity of current Thumper; would 
need to deploy a 2nd thumper, ... which could potentially grow into "mount map" 
nightmare right?

2.  unless a Gluster/Unify type of solution would be able to address?  but 
Gluster/Unify, would mean no NFS with cache, back again to how to address small 
random IO ...

just wanting to note the various scenarios ...

thanks again for the enlightenment .. I think I'll also post in the gluster 
list querying on gluster on thumper configurations ...

thanks!!!

- a.
-- 
This message posted from opensolaris.org
_______________________________________________
storage-discuss mailing list
[email protected]
http://mail.opensolaris.org/mailman/listinfo/storage-discuss

Reply via email to