11:05 p.m.
Hi,
-----Original Message-----
From: hpdd-discuss-bounces(a)lists.01.org [mailto:hpdd-discuss-
bounces(a)lists.01.org] On Behalf Of Bob Ball
Sent: Wednesday, July 10, 2013 8:00 AM
To: Christopher J. Walker
Cc: hpdd-discuss(a)ml01.01.org
Subject: Re: [HPDD-discuss] Shirinking the mdt volume
Thanks for that hint, Chris. Re-running my getfattr now.
bob
On 7/10/2013 9:41 AM, Christopher J. Walker wrote:
> On 10/07/13 01:56, Bob Ball wrote:
>> When we set up our mdt volume, lo these many years past, we did it
>> with a 2TB volume. Overkill. About 17G is actually in use.
>>
>> This is a Lustre 1.8.4 system backed by about 450TB of OST on 8
>> servers. I would _love_ to shrink this mdt volume to a more
>> manageable size, say, 50GB or so, as we are now in a down time before
>> we upgrade to Lustre 2.1.6 on SL6.4. I have taken a "dd" of the
>> volume, and am now in the process of doing getfattr -R -d -m '.*' -P
>> . > /tmp/mdt_ea.bak after which I will do a tar czf {backup file}.tgz
>> --sparse /bin/tar is the SL5 version tar-1.20-6.x86_64. This
This may be a moot point now, but will add it anyway:
There are many versions of 'tar' about that support 'xattrs', but not all
of them work with Lustre's xattrs. For RHEL-based distro's, I believe you need to
get the distro's tar at v1.25 or greater to have the Lustre patches included. For
sites running earlier versions of the OS, like SL5, there is yet another version of tar
that does support Lustre xattrs. It can be found here:
https://wiki.hpdd.intel.com/display/PUB/Lustre+Tools
--
Brett Lee
Sr. Systems Engineer
Intel High Performance Data Division
>> supports the --xattrs switch. So, a choice here, should I
instead
>> use the --xattrs switch on the tar, or should I use --no-xattrs since
>> the mdt_ea.bak will have all of them?
>>
>> What are my prospects for success, if I restore that tar file to a
>> smaller volume, then apply the attr backup, before I upgrade?
>>
>> Answers and advice are greatly appreciated.
>>
> Not a direct answer, but you should read:
>
> https://jira.hpdd.intel.com/browse/LUDOC-131
>
> In essence, if your filesystem has extended attributes, or ACLs, when
> you mount the mdt as an ldiskfs filesystem, you need to explicitly
> specify them. What I should have done is:
>
> mount -t ldiskfs -o user_xattr -o acl /dev/sdb /mnt/mgs
>
> Otherwise the extended attributes and acls of the files are lost to
> the lustre filesystem.
>
>
> Chris
> _______________________________________________
> HPDD-discuss mailing list
> HPDD-discuss(a)lists.01.org
> https://lists.01.org/mailman/listinfo/hpdd-discuss
>
_______________________________________________
HPDD-discuss mailing list
HPDD-discuss(a)lists.01.org
https://lists.01.org/mailman/listinfo/hpdd-discuss