Alex
2008-Nov-04 13:54 UTC
[Lustre-discuss] Replacing An Existing OST with a bigger one (unsupported optional features)?!
[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)
[root at shd1 ~]# umount /dev/hdb1
[root at shd1 ~]# mount /dev/hdb1 -t ext3 /mnt/ost_old
mount: wrong fs type, bad option, bad superblock on /dev/hdb1,
missing codepage or other error
In some cases useful info is found in syslog - try
dmesg | tail or so
[root at shd1 ~]#
[root at shd1 ~]# dmesg |tail -1
EXT3-fs: hdb1: couldn''t mount because of unsupported optional features
(40).
[root at shd1 ~]#
So, i can''t mount /dev/hdb1 as EXT3, as explained on section
"22.3.13
Replacing An Existing OST or MDS" in order to migrate data from it to
another
volume!
Somebody can help me?
Regards,
Alx
Wojciech Turek
2008-Nov-04 14:16 UTC
[Lustre-discuss] Replacing An Existing OST with a bigger one (unsupported optional features)?!
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) > > [root at shd1 ~]# umount /dev/hdb1 > > [root at shd1 ~]# mount /dev/hdb1 -t ext3 /mnt/ost_old > mount: wrong fs type, bad option, bad superblock on /dev/hdb1, > missing codepage or other error > In some cases useful info is found in syslog - try > dmesg | tail or so > [root at shd1 ~]# >Try mount -t ldiskfs /dev/hdb1 /mnt/ost_old> [root at shd1 ~]# dmesg |tail -1 > EXT3-fs: hdb1: couldn''t mount because of unsupported optional features (40). > [root at shd1 ~]# > > So, i can''t mount /dev/hdb1 as EXT3, as explained on section "22.3.13 > Replacing An Existing OST or MDS" in order to migrate data from it to another > volume! > > Somebody can help me? > > Regards, > Alx > _______________________________________________ > Lustre-discuss mailing list > Lustre-discuss at lists.lustre.org > http://lists.lustre.org/mailman/listinfo/lustre-discuss >
Alex
2008-Nov-04 14:28 UTC
[Lustre-discuss] Replacing An Existing OST with a bigger one (unsupported optional features)?!
> > [root at shd1 ~]# mount /dev/hdb1 -t ext3 /mnt/ost_old > > mount: wrong fs type, bad option, bad superblock on /dev/hdb1, > > missing codepage or other error > > In some cases useful info is found in syslog - try > > dmesg | tail or so > > [root at shd1 ~]# > > Try mount -t ldiskfs /dev/hdb1 /mnt/ost_oldIs working :-) Thanks for the tip! Regards, Alx
Brian J. Murrell
2008-Nov-04 14:50 UTC
[Lustre-discuss] Replacing An Existing OST with a bigger one (unsupported optional features)?!
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.
Alex
2008-Nov-04 16:00 UTC
[Lustre-discuss] Replacing An Existing OST with a bigger one (unsupported optional features)?!
> > [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.Hi Brian, You are very vigilantly with my setup :-) ... You are absolutely right! I am using 2 slices because i am learning/testing Lustre and i don''t have enough equipments and hard disks in order to add more OSTs, so i used one disk with 2 partitions to emulate somehow the second OST :-)). Indeed, i agree with you: on production this setup should be avoided. Thanks again. You are a nice guy ;-) Regards, Alx