> > > 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
