[Beowulf] how cluster's storage can be flexible/expandable?

Christopher Samuel samuel at unimelb.edu.au
Thu Nov 8 22:19:36 PST 2012


-----BEGIN PGP SIGNED MESSAGE-----
Hash: SHA1

On 09/11/12 14:47, Duke Nguyen wrote:

> I don't understand how the cluster's storage can be expandable on
> the fly (hot swap?) without affecting current data and usage.

You use an appliance, filesystem, or intermediate layer like lVM that
allows you to add space and increase the filesystem on the fly.

So JBODs with LVM on top and XFS on top of that could be resized on
the fly.  You can do the same with ext[34] as well (from memory).

You can grow GPFS on the fly too - in fact we'll shortly be bringing
up a new (larger) storage system, adding it to our GPFS pool and then
telling GPFS to migrate data from the old system to the new one whilst
the whole system is live.

I think the same is possible with Lustre, GlusterFS and Ceph too.

Then there are things like Panasas where you can buy more shelves and
add them to the bladeset and expand that way.

cheers!
Chris
- -- 
 Christopher Samuel        Senior Systems Administrator
 VLSCI - Victorian Life Sciences Computation Initiative
 Email: samuel at unimelb.edu.au Phone: +61 (0)3 903 55545
 http://www.vlsci.org.au/      http://twitter.com/vlsci

-----BEGIN PGP SIGNATURE-----
Version: GnuPG v1.4.11 (GNU/Linux)
Comment: Using GnuPG with Mozilla - http://www.enigmail.net/

iEYEARECAAYFAlCcoHgACgkQO2KABBYQAh9uTgCgiVDV1A2PlsyU6Gyh09QPU77j
oFQAn0PRku2cvanegCxNj5mZFeJqvo0q
=/Sfn
-----END PGP SIGNATURE-----


More information about the Beowulf mailing list