Lustre discuss - May 2006 - Access Lustre from Client Machine: Error message, get_lov_tgts failed, using get_refs

On Feb 23, 2006  17:13 -0800, J Tafas wrote:
> I got this error message when I tried to run Lustre from my client machine,
> Here is the command that I typed:
> # lconf --verbose --node=client /home1/lustre/server1.xml
>  
> And here is the result that I got. 
>  
> root@myserver:/# lconf --verbose --node=client /home1/lustre/server1.xml
> Service: ldlm ldlm ldlm_UUID
> Service: mountpoint MNT_client MNT_client_UUID
> get_lov_tgts failed, using get_refs
> /mnt/lustre already mounted.
>  
> It failed to get the logical object volume, using get_refs? What cause
that?
This message is a red herring.  What is the real culprit is the last one:
"/mnt/lustre already mounted".  The lconf script is looking in
/proc/mounts
and sees that you already have a lustre mount at /mnt/lustre, so I''d
guess
you are not having any problems at all.

Just FYI, since Lustre runs entirely in the kernel the majority of error
messages will go to /var/log/messages, or "dmesg", so if you have any
problems that is usually the place to check.

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

Hello everybody, 
 
I got this error message when I tried to run Lustre from my client machine,
Here is the command that I typed:
# lconf --verbose --node=client /home1/lustre/server1.xml
 
And here is the result that I got. 
 
root@myserver:/# lconf --verbose --node=client /home1/lustre/server1.xml
configuring for host:  [''client'']
nid: xxx.xxx.xxx.xxx
add_local NET_client_tcp_UUID
find_local_routes: []
setting /proc/sys/net/core/rmem_max to at least 16777216
setting /proc/sys/net/core/wmem_max to at least 16777216
Service: network NET_client_tcp NET_client_tcp_UUID
nid: xxx.xxx.xxx.xxx
Service: ldlm ldlm ldlm_UUID
Service: mountpoint MNT_client MNT_client_UUID
get_lov_tgts failed, using get_refs 
+ sysctl portals/debug_path /tmp/lustre-log-server13
+ /usr/sbin/lctl  modules > /tmp/ogdb-server13
Service: network NET_client_tcp NET_client_tcp_UUID
nid: xxx.xxx.xxx.xxx
Service: ldlm ldlm ldlm_UUID
Service: mountpoint MNT_client MNT_client_UUID
get_lov_tgts failed, using get_refs
/mnt/lustre already mounted.
 
It failed to get the logical object volume, using get_refs? What cause that?

 
Thank you for your help 
-----------
Pencil, Paper, and FPGA... what else do I  need...?
 
 
-------------- next part --------------
An HTML attachment was scrubbed...
URL:
http://mail.clusterfs.com/pipermail/lustre-discuss/attachments/20060223/5d25a6af/attachment.html