[lustre-discuss] mkfs.lustre for ZFS draid

[Thomas Roth]

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
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.lustre.org/pipermail/lustre-discuss-lustre.org/attachments/20250206/8f8d1708/attachment.htm>