On Feb 02, 2007  17:17 -0600, Kevin L. Buterbaugh wrote:
> OK, I think I'm getting somewhere.  I noticed that the activity light on 
> my actual storage array was going crazy.  Does Lustre have to do some 
> sort of filesystem creation that would take quite a while for a pair of 
> 1.25 TB LUNs?

Well, it does have to format them, but that currently happens at mkfs time
and not at first mount.  I'm not sure of the actual format times, but they
should be in the neighbourhood of 5 minutes or so.

> I also did a test.  Instead of specifying my OST's as the actual LUNs on 
> the storage arrays, instead I specified them as:
> 
> lmc -m config.xml --add ost --node lustre1 --lov lov-test --ost 
> ost1-test --fstype ldiskfs --dev /tmp/ost1-test --size 100000
> lmc -m config.xml --add ost --node lustre2 --lov lov-test --ost 
> ost2-test --fstype ldiskfs --dev /tmp/ost2-test --size 100000

This means you are putting your OSTs into the root filesystem and not
onto your storage arrays.  This is fine for basic sanity testing but
is not desirable for production use.

> I reran config.sh and lconf on the OST's and MDS and voila!  I can mount 
> the filesystem successfully!

This would imply something wrong with your storage arrays.

You didn't include the OST syslogs in the first message, do you still
have those from your first attempt?

Cheers, Andreas
--
Andreas Dilger
Principal Software Engineer
Cluster File Systems, Inc.

_______________________________________________
Lustre-discuss mailing list
[email protected]
https://mail.clusterfs.com/mailman/listinfo/lustre-discuss

Reply via email to