Introduction to Moab for users » History » Version 3
Version 2 (Miguel Dias Costa, 29/02/2012 15:48) → Version 3/4 (Miguel Dias Costa, 29/02/2012 15:49)
h1. Introduction to Moab for users
Moab is the workload management system that is used in FEUP's high performance computing clusters.
h2. Getting started
After gaining ssh accesh to a moab frontend, a user can see what resources are available and check the status of the queue by running
<pre>
mshow
</pre>
In order to submit jobs, one needs to create a submit script that defines the requirements and the command to be executed. A simple example to get started would be
h3. Example serial job submission script helloworld.submit
<pre>
#!/bin/bash
#MOAB -l nodes=1:ppn=1
#MOAB -l partition=torque1
#MOAB -j oe
cd $PBS_O_WORKDIR
#!/bin/bash
echo "----------------------"
hostname
echo "----------------------"
date
echo "----------------------"
echo "Sleeping 20s"
sleep 20
echo "----------------------"
echo "Hello World!"
</pre>
h3. Example parallel job submission script helloworld.submit
<pre>
#!/bin/bash
#MOAB -l nodes=2:ppn=2
#MOAB -l partition=torque1
#MOAB -j oe
cd $PBS_O_WORKDIR
mpirun -np 4 -machinefile $PBS_NODEFILE ./command | tee $PBS_JOBID.output
</pre>
After creating this file, the job would be submitted by running
<pre>
msub helloworld.submit
</pre>
h2. Checking status
To see details about the status of each job in the queue, one would run
<pre>
mshow
</pre>
To check the status of a specific job,
<pre>
checkjob jobid
</pre>
To check the status of a specific node,
<pre>
checknode nodeid
</pre>
To cancel a job
<pre>
canceljob jobid
</pre>
h2. More Information
http://www.adaptivecomputing.com/resources/docs/
Moab is the workload management system that is used in FEUP's high performance computing clusters.
h2. Getting started
After gaining ssh accesh to a moab frontend, a user can see what resources are available and check the status of the queue by running
<pre>
mshow
</pre>
In order to submit jobs, one needs to create a submit script that defines the requirements and the command to be executed. A simple example to get started would be
h3. Example serial job submission script helloworld.submit
<pre>
#!/bin/bash
#MOAB -l nodes=1:ppn=1
#MOAB -l partition=torque1
#MOAB -j oe
cd $PBS_O_WORKDIR
#!/bin/bash
echo "----------------------"
hostname
echo "----------------------"
date
echo "----------------------"
echo "Sleeping 20s"
sleep 20
echo "----------------------"
echo "Hello World!"
</pre>
h3. Example parallel job submission script helloworld.submit
<pre>
#!/bin/bash
#MOAB -l nodes=2:ppn=2
#MOAB -l partition=torque1
#MOAB -j oe
cd $PBS_O_WORKDIR
mpirun -np 4 -machinefile $PBS_NODEFILE ./command | tee $PBS_JOBID.output
</pre>
After creating this file, the job would be submitted by running
<pre>
msub helloworld.submit
</pre>
h2. Checking status
To see details about the status of each job in the queue, one would run
<pre>
mshow
</pre>
To check the status of a specific job,
<pre>
checkjob jobid
</pre>
To check the status of a specific node,
<pre>
checknode nodeid
</pre>
To cancel a job
<pre>
canceljob jobid
</pre>
h2. More Information
http://www.adaptivecomputing.com/resources/docs/