[torqueusers] pbs_mom unable to chdir to automounted dirs
chemadm at hamilton.edu
Wed Oct 22 07:52:41 MDT 2008
Hmm... strange. I am using torque 2.2.1. I use automounted nfs dirs
and don't seem to have any problems like that. Given that jobs work
for you after it gets mounted I'd be willing to think it might be
something with automounter. Sorry I have no other idea's for you.
Hopefully someone else might be able to chime in with something.
On Oct 22, 2008, at 9:21 AM, Mary Ellen Fitzpatrick wrote:
> Thanks Steve. Yes I already have my config file listed as such
> $usecp *:/fs/userB1 /fs/userB1
> Once the /fs/userB1 is automounted, I get all of my output files
> delivered properly. Just seems like pbs_mom needs to tell the
> compute node to mount /fs/userB1 before running the job.
> Steve Young wrote:
>> I'm not for certain but I wonder if you put this in your mom_priv/
>> config on your nodes?
>> $usecp *:/home /home
>> (of course change the /home to your directory names). Hope this
>> On Oct 21, 2008, at 4:20 PM, Mary Ellen Fitzpatrick wrote:
>>> I have my home dirs nfs exported to all of my compute nodes. I
>>> can log into the nodes and cd the nfs mounted dirs, no problem.
>>> When I submit a job to a node and the automounted nfs dirs are
>>> not mount (timed out), I get the following error:
>>> Oct 21 16:08:14 node1047 pbs_mom: No such file or directory (2)
>>> in TMomFinalizeChild, PBS: chdir to '/fs/userB1/mfitzpat' failed:
>>> No such file or directory
>>> If I immediately resubmit the job to the same node, it will run.
>>> It appears that pbs wants the automounted nfs dirs to be already
>>> mounted, then the job will run. If I hard mount the nfs home
>>> dirs, I have no problem running the jobs, but I do not want to do
>>> Any one run into this? Trying to figure out if it is a torque
>>> issue or automount issue.
>>> Mary Ellen
>>> torqueusers mailing list
>>> torqueusers at supercluster.org
> Mary Ellen
More information about the torqueusers