23.07.2014 Views

Lustre 1.6 Operations Manual

Lustre 1.6 Operations Manual

Lustre 1.6 Operations Manual

SHOW MORE
SHOW LESS

You also want an ePaper? Increase the reach of your titles

YUMPU automatically turns print PDFs into web optimized ePapers that Google loves.

Mounting <strong>Lustre</strong> on a client node<br />

$ mkdir -p /mnt/testfs<br />

$ mount -t lustre cfs21@tcp:0:/testfs /mnt/testfs<br />

The MGS and the MDT can be run on separate devices. With the MGS on node<br />

’mgs16’:<br />

$ mkfs.lustre --mgs /dev/sda1<br />

$ mkdir -p /mnt/mgs<br />

$ mount -t lustre /dev/sda1 /mnt/mgs<br />

$ mkfs.lustre --fsname=spfs --mdt --mgsnode=mgs16@tcp0 /dev/sda2<br />

$ mkdir -p /mnt/test/mdt<br />

$ mount -t lustre /dev/sda1 /mnt/test/mdt<br />

If the MGS node has multiple interfaces (for example, mgs16 and 1@elan), only the<br />

client mount command has to change. The MGS NID specifier must be an<br />

appropriate nettype for the client (for instance, TCP client could use uml1@tcp0 and<br />

Elan client could use 1@elan). Alternatively, a list of all MGS NIDs can be provided<br />

and the client chooses the correct one.<br />

$ mount -t lustre mgs16@tcp0,1@elan:/spfs /mnt/spfs<br />

Reformat a device that has already been formatted with mkfs.lustre<br />

$ mkfs.lustre --fsname=spfs --mdt --mgs --reformat /dev/sda1<br />

Note – Error -19 = -ENODEV (from /usr/include/asm/errno.h) occurs when the<br />

client tries to connect to the server and fails to export the <strong>Lustre</strong> filesystem. The<br />

scenario can be: shut down the service, start up the service, fail over to another<br />

server node (if you have failover configured), or configuration errors.<br />

Chapter 4 <strong>Lustre</strong> Installation 4-7

Hooray! Your file is uploaded and ready to be published.

Saved successfully!

Ooh no, something went wrong!