Hi all, how are the "redundancy groups" in a ZFS draid specified if you want to format them as Lustre OSTs?
I'm used to creating a zpool first, as in `zpool create .... raidz2 osspool0 */dev/*...`, and then formatting by `mkfs.lustre --ost ... osspool0/ost0` - the OST ost0 will be the only vdev on the pool osspool0, eventually it will occupy all of that zpool. In a draid, I will put all disks into one "pool", e.g. with 70 disks I will do something like `zpool create ... draid2:8d:70c:2s`, which should/might result in 7 redudancy groups, the equivalent of the earlier raidz-2 ? But how can I address them when running mkfs.lustre, if I still want to get 7 OSTs out of it? Regards, Thomas
_______________________________________________ lustre-discuss mailing list [email protected] http://lists.lustre.org/listinfo.cgi/lustre-discuss-lustre.org
