Re: [HPDD-discuss] zfs on linux and lustre
On 2014/10/16, 9:10 AM, "Kurt Strosahl" <strosahl(a)jlab.org> wrote:
Good Morning,
Has anyone out there been using zfs as the back end for lustre? I am
curious as to how you set up raid-z when setting up an ost.
Two options exist:
- specify raidz/raidz2 on mkfs.lustre command line (see man page):
mkfs.lustre {other opts} --ost --backfstype=zfs mypool/testfs-OST0000 \
raidz2 /dev/sd[a-j] raidz2 /dev/sd[k-t] raidz2 /dev/sd[u-z]
/dev/sda[a-d]
would, for example, create three RAID-Z2 VDEVs with 10 disks each. Of
course the use of /dev/sd* device names is frowned upon in real life ZFS
usage, but are shorter for this example.
- create RAID-Z/Z2 datasets normally, then just point mkfs.lustre at them:
mkfs.lustre {other opts} --ost --backfstype=zfs mypool/testfs-OST0000
IIRC you have to disable automatic mounting on the pool (legacy mode).
Cheers, Andreas
--
Andreas Dilger
Lustre Software Architect
Intel High Performance Data Division