[Lustre-discuss] Replacing An Existing OST with a bigger one (unsupported optional features)?!

[Brian J. Murrell]

On Tue, 2008-11-04 at 15:54 +0200, Alex wrote:
> [root at rs1 ~]# lfs df -h
> UUID                     bytes      Used Available  Use% Mounted on
> testfs-MDT0000_UUID     130.4G    460.1M    122.5G    0% /mnt/lustre[MDT:0]
> testfs-OST0000_UUID      18.3G     17.4G      2.0M   94% /mnt/lustre[OST:0]
> testfs-OST0001_UUID      18.3G     15.5G      2.0G   84% /mnt/lustre[OST:1]
> testfs-OST0002_UUID      36.7G     15.5G     19.4G   42% /mnt/lustre[OST:2]
> testfs-OST0003_UUID      36.7G     15.5G     19.4G   42% /mnt/lustre[OST:3]
> filesystem summary:     110.0G     63.8G     40.7G   57% /mnt/lustre
> [root at rs1 ~]#
> 
> Now, supposing that i want to REPLACE OST:0 (which is full) with a larger one 
> block device and keep all data intact, i do:
> 1. umount /mnt/lustre on all our clients - ok
> 2. go to shd1 (OSS machine which is keeping hdb1 as OST:0)
> 
> [root at shd1 ~]# mount
> ...
> /dev/hdb2 on /mnt/lustre/ost1_02 type lustre (rw,_netdev)
> /dev/hdb1 on /mnt/lustre/ost1_01 type lustre (rw,_netdev)

So it appears that you have a single disk (hdb) partitioned into at
least 2 partitions with partition 1 being ~18G and partition 2 likely
being ~18G as well.  I'm wondering why.  Are there any more partitions
on hdb?

There is usually no advantage (and with some hardware there is even a
disadvantage) to making partitions on a disk to be used as OSTs in the
same Lustre filesystem except for limiting them to the 8TiB max. OST
limit.

If you want to use the entirety of a disk for an OST or MDT, usually you
can just use the whole disk device (i.e. /dev/hdb) and dispense with the
whole partitioning mess altogether.

b.