HPC FAQ

How do I use PBS?

PBS at TPAC

The Portable Batch Systems (PBS) used at TPAC vary between compute systems.  Vortex and Katabatic use Maui/Torque package while Eddy and Kunanyi use open-source PBS Pro.  The following is intended to be generic across both PBS types.

Quick Syntax guide

qstat

 

Standard queue status command supplied by PBS. See man qstat for details of options. (But see the local nqstat command below.)
nqstat Local version of qstat. The queue header of nqstat gives the limit on wall clock time and memory for you and your project. The fields in the job lines are fairly straightforward.
qdel jobid Delete your unwanted jobs from the queues. The jobid is returned by qsub at job submission time, and is also displayed in the nqstat output.
qsub Submit jobs to the queues. The simplest use of the qsub command is typified by the following example (note that there is a carriage-return after -l wd and ./a.out):

 

$ qsub -P a99 -q normal -l walltime=20:00:00,mem=300MB -l wd
./a.out
^D     (that is control-D)

or

$ qsub -P a99 -q normal -l walltime=20:00,mem=300MB -l wd jobscript

where jobscript is an ascii file containing the shell script to run your commands (not the compiled executable which is a binary file).
More conveniently, the qsub options can be placed within the script to avoid typing them for each job:

#!/bin/bash
#PBS -P a99
#PBS -q normal
#PBS -l walltime=20:00:00,mem=300MB
#PBS -l wd
./a.out

You submit this script for execution by PBS using the command:

$ qsub jobscript

You may need to enter data to the program and may be used to doing this interactively when prompted by the program.

There are two ways of doing this in batch jobs.

If, for example, the program requires the numbers 1000 then 50 to be entered when prompted. You can either create a file called, say, input containing these values

$ cat input
1000
50

then run the program as

./a.out < input

or the data can be included in the batch job script as follows:

#!/bin/bash
#PBS -P a99
#PBS -q normal
#PBS -l walltime=20:00:00,mem=300MB
#PBS -l wd
./a.out << EOF
1000
50
EOF

Notice that the PBS directives are all at the start of the script, that there are no blank lines between them, and there are no other non-PBS commands until after all the PBS directives.

qsub options of note:

-P project The project which you want to charge the jobs resource usage to. The default project is specified by the PROJECT environment variable.
-q queue Select the queue to run the job in. The queues you can use are listed by running nqstat.
-l walltime=??:??:?? The wall clock time limit for the job. Time is expressed in seconds as an integer, or in the form:
[[hours:]minutes:]seconds[.milliseconds]
System scheduling decisions depend heavily on the walltime request – it is always best to make as accurate a request as possible.
-l mem=???MB The total memory limit across all nodes for the job – can be specified with units of “MB” or “GB” but only integer values can be given. There is a small default value.
Your job will only run if there is sufficient free memory so making a sensible memory request will allow your jobs to run sooner.A little trial and error may be required to find how much memory your jobs are using – nqstat lists jobs actual usage.
-l ncpus=? The number of cpus required for the job to run on. The default is 1.

 -l ncpus=N – If the number of cpus requested, N, is small (currently 16 or less on NF systems) the job will run within a single shared memory node.

If the number of cpus specified is greater, the job will be distributed over multiple nodes. Currently on NF systems, these larger requests are restricted to multiples of 16 cpus.

-l jobfs=???GB The requested job scratch space. This will reserve disk space, making it unavailable for other jobs, so please do not over estimate your needs.

Any files created in the $PBS_JOBFS directory are automatically removed at the end of the job. Ensure that you use integers, and units of mb, MB, gb, or GB.

-l software=??? Specifies licensed software the job requires to run. See the software for the string to use for specific software.

The string should be a colon separated list (no spaces) if more than one software product is used.

If your job uses licensed software and you do not specify this option (or mis-spell the software), you will probably receive an automatically generated email from the license shadowing daemon, and the job may be terminated.

You can check the lsd status and find out more by looking at the license status website.

-l other=??? Specifies other requirements or attributes of the job. The string should be a colon separated list (no spaces) if more than one attribute is required. Generally supported attributes are:

  • iobound – the job should not share a node with other IO bound jobs
  • mdss – the job requires access to the MDSS (usually via the mdss command). If MDSS is down, the job will not be started.
  • gdata1 – the job requires access to the /g/data1. If /g/data1 filesystem is down, the job will not be started.
  • pernodejobfs – the job’s jobfs resource request should be treated as a per node request.
    Normally the jobfs request is for total jobfs summed over all nodes allocated to the job (like mem). Only relevant to distributed parallel jobs using jobfs.

You may be asked to specify other options at times to support particular needs or circumstances.

-r y Specifies your job is restartable, and if the job is executing on a node when it crashes, the job will be requeued.

Both resources used by and resource limits set for the original job will carry over to the requeued job.
Hence a restartable job must be checkpointing such that it will still be able to complete in the remaining walltime should it suffer a node crash.

The default is that jobs are assumed to not be restartable.
Note that regardless of the restartable status of a job, time used by jobs on crashed nodes is charged against the project they are running under,
since the onus is on users to ensure minimum waste of resources via a checkpointing mechanism which they must build into any particularly long running codes.

-l wd Start the job in the directory from which it was submitted. Normally jobs are started in the users home directory.

 

qps jobid  show the processes of a running job
qls jobid  list the files in a job’s jobfs directory
qcat jobid  show a running job’s stdout, stderr or script
qcp jobid  copy a file from a running job’s jobfs directory

 

The man pages for these commands on the system detail the various options you will probably need to use.

How do I connect to the HPC systems?

An SSH client is required to connect to all HPC systems.  For windows users the PuTTY client is a good free client but there are many others.  Mac OS X users can use the builtin Terminal app.

Your account will have been enabled only for the HPC system appropriate for your project(s).

How do I get further assistance?

Requests to TPAC helpdesk can be submitted online via the TPAC Jira Portal or via email to helpdesk@tpac.org.au.  Through the Jira portal you will be able to track the progress of your request.

What are the Basic Unix commands that one needs to know to use the linux cluster?

How to get online help

To find a command or library routine that performs a required function, try searching by keyword e.g.

man -k keyword
or
apropos keyword

Use “man command_name” to find details on how to use a unix command or library e.g.

man cat
man ls

If no man page is found, try “info command_name” e.g.

info module

Manipulating files and directories

  • ls
    List contents of current directory
  • cd
    Change directory
  • rm
    Remove file of directory
  • mkdir
    Make a new directory

Use the “man” command for more information on the above.

A few notes on Unix directory names.

A Unix file full path name is constructed of the directory and subdirectory names separated by slashes “/”. ie. /u/jsmith/work/file1.  When you first login you will be in your “home” directory at TPAC this is usually /u/username.  In most shells this can also be referenced as ~username.

For example if your username is asmith then “cd ~asmith/work” will take you to the “work” directory in your home directory.

All Unix full path names start with “/”, (There are no Drive/Volume names as in Windows). Hence any filename starting with “/” is a full pathname.

A filename containing one or more slashes “/” will refer to a subdirectory of the “current working directory”.  The current working directory may also be referenced as dot “.” i.e. ./subdirectory/file.

The parent of the “current working directory” may be referenced as dot-dot “..”.  For example if you have two directories in your home directory work1 and work2 and you cd to work1 you can then change to work2 by typing the command “cd ../work2”.

 

What application/software is available?

On each of the compute systems you can run “module avail” which will provide a list of installed software and their versions.  Additional software and or versions can be requested via the TPAC helpdesk or email to helpdesk@tpac.org.au.

How do I capture the STDOUT and STDERR generated by my job?

If the application you are running on a node produces output on STDOUT it is important to ensure that this output is captured to a file in your home directory.  If it isn’t redirected it will be captured to a file within the node’s local storage which has limited space.  If the local storage file system fills up it may cause the job that is running to terminate early or produce inconsistent data.

It is recommended that you use the -e and -o options when running qsub.  To ensure these are not forgotten it would be best to create a shell script to start your job as follows:

start_job.sh:
#!/bin/bash

qsub -e errors.txt -o output.txt pbs_job.sh

 

Alternatively the output can be redirected in the pbs_job.sh using the standard STDOUT and STDERR redirection operators.  Refer to “What are the shells control and redirection operators” for more information.

 

How can I monitor the progress of my PBS jobs?

Use “qstat -f” to provide information about the current status of the job.

In your job startup script you should redirect STDOUT to a file in your home directory.  This may give you information about what the job is doing depending on your application.

 

How do I specify memory allocation in the pbsscript?

The queuing system is now enforcing memory limits on jobs.  If you do not specify a “mem” limit for your job you will receive the default mem limit of 600mb. This corresponds to:

#PBS -l mem=600mb

If your job uses more memory per thread than this and you do not explicitly ask for more, your job will be killed by the pbs scheduler.  If your job uses less than this and you do not specify, you will simply be telling pbs that your job needs more memory than it actually uses which will make that memory unavailable to other jobs.  It is best if your mem setting accurately reflects your jobs actual memory requirements.