General Usage of Hydra: Difference between revisions

From csml-wiki.northwestern.edu
Jump to navigation Jump to search
No edit summary
m (added physical memory limit option)
 
(4 intermediate revisions by 2 users not shown)
Line 7: Line 7:
<li>Example of job.pbs file
<li>Example of job.pbs file
<pre>
<pre>
### AUTOMATICALLY GENERATED BATCH FILE
### AUTOMATICALLY GENERATED BATCH FILE


# ### name of job
# ### name of job
#PBS -N [name_of_job]
#PBS -N [name_of_job]


# ### mail for begin/end/abort
# ### mail for end/abort
#PBS -m ea
#PBS -m ea
#PBS -M [email_address]
#PBS -M [email_address]


# ### maximum wall time
# ### maximum wall time
#PBS -l walltime=30:00:00:00
#PBS -l walltime=[dd:hh:mm:ss]

# ### maximum physical memory required (use 'kb', 'mb', or 'gb')
#PBS -l mem=512mb


# ### number of nodes and processors per node
# ### number of nodes and processors per node
#PBS -l nodes=1:ppn=1
#PBS -l nodes=1:ppn=1


# # ### queue
# ### queue
###PBS -q [queue]
#PBS -q [queue_name]


# ### indicates that job should not rerun if it fails
# ### indicates that job should not rerun if it fails
Line 52: Line 55:
<tt>[dd:hh:mm:ss]</tt>
<tt>[dd:hh:mm:ss]</tt>
This is the maximum allowed running time for your job. dd: days; hh: hours; mm: minutes; ss: seconds.
This is the maximum allowed running time for your job. dd: days; hh: hours; mm: minutes; ss: seconds.

<tt>[queue_name]</tt>
There are two options for queue name: fast or default.


<tt>[job_location]</tt>
<tt>[job_location]</tt>
Line 69: Line 75:
qstat -u [username]
qstat -u [username]
</pre>
</pre>
where <tt>[username]</tt> is your own user name. This command will show the status of your own jobs.
where <tt>[username]</tt> is your own username. This command will show the status of your own jobs.
</ul>
</ul>

Latest revision as of 17:12, 10 October 2015

  • Login
    ssh hydra  
    
  • Example of job.pbs file
    ### AUTOMATICALLY GENERATED BATCH FILE
    
    # ### name of job
    #PBS -N [name_of_job]
    
    # ### mail for end/abort
    #PBS -m ea
    #PBS -M [email_address]
    
    # ### maximum wall time
    #PBS -l walltime=[dd:hh:mm:ss]
    
    # ### maximum physical memory required (use 'kb', 'mb', or 'gb')
    #PBS -l mem=512mb
    
    # ### number of nodes and processors per node
    #PBS -l nodes=1:ppn=1
    
    # ### queue
    #PBS -q [queue_name]
    
    # ### indicates that job should not rerun if it fails
    #PBS -r n
    
    # ### stdout and stderr merged as stderr
    #PBS -j eo
    
    # ### write stderr to file
    #PBS -e log.err
    
    # ### the shell that interprets the job script
    #PBS -S /bin/bash
    
    cd /home/[job_location]
    time /opt/lammps/lmp2013 < input.dat
    
    if [ $? -eq 0 ] ; then
    touch COMPLETED
    fi
    

    [name_of_job] This is the name of the job that will be showed in the queue.

    [email_address] This is the email address you used to receive the system notice when job begins, aborted or ended.

    [dd:hh:mm:ss] This is the maximum allowed running time for your job. dd: days; hh: hours; mm: minutes; ss: seconds.

    [queue_name] There are two options for queue name: fast or default.

    [job_location] This is the address of the folder where your input file is located.

  • Submit jobs
    qsub job.pbs
    
  • Check job status
    qstat
    

    show status of all jobs.

    qstat -u [username]
    

    where [username] is your own username. This command will show the status of your own jobs.