[torqueusers] qsub/mpirun problems

Glen Beane glen.beane at gmail.com
Thu Sep 18 05:32:45 MDT 2008


On Thu, Sep 18, 2008 at 7:22 AM, Glen Beane <glen.beane at gmail.com> wrote:

>
>
> On Wed, Sep 17, 2008 at 10:06 PM, Zhiliang Hu <zhu at iastate.edu> wrote:
>
>> Sorry for cross posting -- I didn't get the problem solved on other lists:
>>
>> We are running a Linux CentOS 8-node cluster. When "qsub" a mpiblast job,
>> I came to this dilemma: what's the correct way to supply the nodes
>> information: to "qsub" (-l nodes=6:ppn=2)? or to "mpirun" (-np 12
>> -machinefile /path/to/mpimachines)?  Or both? --- they all failed in my
>> trials (details below).
>>
>> Any advice it appreciated.
>
>

Hi,  I actually just noticed the problem

(3) will work if you omit —machinefile /path/to/machines/file

It appears you are using OpenMPI.  When OpenMPI is compiled with native
TORQUE support (use tm to launch remote processes) you must omit
—machinefile since TM knows about all the nodes assigned to the job by
TORQUE.
-------------- next part --------------
An HTML attachment was scrubbed...
URL: http://www.supercluster.org/pipermail/torqueusers/attachments/20080918/5bba19f1/attachment-0001.html


More information about the torqueusers mailing list