Skip to end of metadata
Go to start of metadata

On Computerome, there are two types of machines:

  • 27 systems each with 32 CPU cores and 1TB of memory
  • Approximately 500 systems each with 28 CPU cores and 128 GB of memory.

We have a new environment which makes use of the modules environment command. So in order to get qsub and msub in you PATH variable execute:


$ module load moab torque

Now you can submit jobs via the command qsub and/or msub.We strongly encourage you to take advantage of modules in your pipelines as it gives you better control of your environment.In order to submit jobs that will run on one node only you will only have to specify the following resources:

  1. How long time you expect the job to run ⇒ '-l walltime=<time>'
  2. How much memory your job requires ⇒ '-l mem=xxxgb'
  3. How many CPUs ⇒ '-l nodes=1:ppn=<number of CPUs>'  ;for the 1TB nodes number of CPUs can be from 1 to 32, for the other nodes it will be from 1 to 28.
  4. The <group_NAME> for your current project ⇒ '-W group_list=<group_NAME> -A <group_NAME>' .

To run a job with 23 CPUs, 100GB memory lasting an hour you can use the command:

$ qsub -W group_list=<group_NAME> -A <group_NAME> -l nodes=1:ppn=23,mem=100gb,walltime=3600 <your script>

or using msub:

$ msub -W group_list=<group_NAME> -A <group_NAME> -l nodes=1:ppn=23,mem=100gb,walltime=3600 <your script>

The parameters nodes, ppn, mem is just an example and you should be change to suit your specific job

Interactive jobs

When you want to test something in the batch system, it is strongly recommended to run in an interactive job, by using the following:

$ qsub -W group_list=<group_NAME> -A <group_NAME> -X -I

This will give you access to a single compute node, where you can perform your testing without affecting other users.

iqsub

Computerome is now offering an even more straightforward way to work interactively, the way you do on your own computer or a local linux server, instead of having to submit everything through the queuing system.Just login and type iqsub and the system will ask you 3 simple questions, after which you'll be redirected to a full, private node.

$ iqsub

[ Interactive job ]

  => [ Select group ]

    => [ Select time needed (non extendable) ]

      => [ Select number of Processors needed (1-28/32)

Under no circumstances should you ever run scripts on the Computerome login node.

Script file example

A script for a file to be submitted with qsub might begin with lines like:


#!/bin/sh
### Note: No commands may be executed until after the #PBS lines
### Account information
#PBS -W group_list=pr_12345 -A pr_12345
### Job name (comment out the next line to get the name of the script used as the job name)
#PBS -N test
### Output files (comment out the next 2 lines to get the job name used instead)
#PBS -e test.err
#PBS -o test.log
### Only send mail when job is aborted or terminates abnormally
#PBS -m n
### Number of nodes
#PBS -l nodes=1:ppn=8 
### Memory
#PBS -l mem=120gb
### Requesting time - format is <days>:<hours>:<minutes>:<seconds> (here, 12 hours)
#PBS -l walltime=12:00:00
### Add current shell environment to job (comment out if not needed)
#PBS -V
### Forward X11 connection (comment out if not needed)
#PBS -X
 
# Go to the directory from where the job was submitted (initial directory is $HOME)
echo Working directory is $PBS_O_WORKDIR
cd $PBS_O_WORKDIR

### Here follows the user commands:
# Define number of processors
NPROCS=`wc -l < $PBS_NODEFILE`
echo This job has allocated $NPROCS nodes

# Load all required modules for the job
module load tools
module load perl/5.20.2
module load <other stuff>

# This is where the work is done
# Make sure that this script is not bigger than 64kb ~ 150 lines, otherwise put in seperat script and execute from here
<your script>

The $PBS... variables are set for the batch job by Torque.

If you already have loaded some modules in your login environment , you do not need to specify them in the jobscript. 
However, we recommend that you do it anyway, since it improves the portability of the jobscript and serves as a reminder of the requirements.

The complete list of variables is documented in Exported batch environment variables.Further examples of Torque batch job submission is documented in Job submission

Specifying a different project account

If you run jobs under different projects, for instance pr_12345 and pr_54321, you must make sure that each project gets accounted for separately in the system's accounting statistics.You specify the relevant project account (for example, pr_54321) for each individual job by using these flags to the qsub command:

$ qsub -W group_list=pr_54321 -A pr_54321 ... 

or in the job script file, add line like this near the top:

#PBS -W group_list=pr_54321 -A pr_54321

Please use project names only by agreement with your project owner.

Estimating job resource requirements

First time you run your script, you may not have a clear picture of what kind of resource requirements it has.To get a rough estimate, you could submit a job to a full node, with large walltime:Regular compute node (aka. 'thinnode'):

$ qsub -W group_list=<group_NAME> -A <group_NAME> -l nodes=1:ppn=28:thinnode,walltime=99:00:00 -m n <script>

Fat node:

$ qsub -W group_list=<group_NAME> -A <group_NAME> -l nodes=1:ppn=32:fatnode,walltime=99:00:00 -m n <script>

To see the actual resource usage, see output from command tracejob

As a result of recent performance and stability improvements to the queuing system, the 'tracejob' command is currently not available to regular users, but must be run as a privileged account on a particular set of servers. 
We are working on providing a solution to this, but in the meantime, please contact Computerome support if you need to get results from 'tracejob'

Alternatively you can add theses linse to the bottom of your script

module load shared moab
checkjob -v $PBS_JOBID

They wil gennerate something like the following:

Total Requested Tasks: 20
Total Requested Nodes: 1
Req[0]  TaskCount: 20  Partition: torque
Dedicated Resources Per Task: PROCS: 1  MEM: 12G
Utilized Resources Per Task:  PROCS: 0.37  MEM: 12G  SWAP: 2020M
Avg Util Resources Per Task:  PROCS: 0.37
Max Util Resources Per Task:  PROCS: 0.80  MEM: 12G  SWAP: 2020M
Average Utilized Memory: 10761.74 MB
Average Utilized Procs: 8.47

To calculate what you should use for the "-l mem=" parameter you have to times the number of tasks with "Max Util Resource Per Task" "MEM:" Here it would bbe 20 * 12 gb = 240gb.


$ tracejob 5306250
/var/spool/torque/server_priv/accounting/20150212: Permission denied
/var/spool/torque/mom_logs/20150212: No such file or directory
/var/spool/torque/sched_logs/20150212: No such file or directory

Job: 5306250.risoe-r04-sn064.cm.cluster

02/12/2015 11:10:22  S    enqueuing into idle, state 1 hop 1
02/12/2015 11:10:37  S    Job Run at request of root@risoe-r04-sn064.cm.cluster
02/12/2015 11:10:37  S    child reported success for job after 0 seconds (dest=???), rc=0
02/12/2015 11:10:37  S    Not sending email: User does not want mail of this type.
02/12/2015 11:10:37  S    Not sending email: User does not want mail of this type.
02/12/2015 11:10:37  S    Exit_status=0 resources_used.cput=00:00:00 resources_used.mem=0kb resources_used.vmem=0kb
                          resources_used.walltime=00:00:00
02/12/2015 11:10:37  S    on_job_exit valid pjob: 5306250.risoe-r04-sn064.cm.cluster (substate=50)
Look at resources_used.xyz for hints.

Requesting a minimum memory size

A number of node features can be requested, see the Torque Job Submission page. For example, you may require a minimum physical memory size by requesting:

$ qsub -W group_list=<group_NAME> -A <group_NAME> -l nodes=2:ppn=16,mem=120gb <your script>

i.e.: 2 entire nodes, 16 CPU cores on each, the total memory of all nodes >= 120 GB RAM.

Do not request the maximum physical amount of RAM, since the RAM memory available to users is slightly less than the physical RAM memory.

To see the available RAM memory sizes on the different nodes types see the Hardware page.

Waiting for specific jobs

It is possible to specify that a job should only run after another job has completed succesfully, please see the -W flags in the qsub page.To run <your script> after job 12345 has completed succesfully::

$ qsub -W depend=afterok:12345 <your script>

Be sure that the exit status of job 12345 is meaningful: if it exits with status 0, you second job will run. If it exits with any other status, you second job will be cancelled.It is also possible to run a job if another job fails (``afternotok``) or after another job completes, regardless of status (``afterany``). Be aware that the keyword ``after`` (as in ``-W depend=after:12345``) means run after job 12345 has *started*.

Submitting jobs to 32-CPU nodes

The quad-processor, 8-core Intel *Sandy Bridge* Xeon E5-4610 v2 nodes (32 CPU cores total) we define to have a node property of fatnode (nodes f001-f027). You could submit a batch job like in these examples:: 2 entire fatnodes, 32 CPUs each, total 64 CPU cores

$ qsub -W group_list=<group_NAME> -A <group_NAME> -l nodes=2:ppn=32:fatnode <your script>

Explicitly the f015 node, 32 CPU cores:

$ qsub -W group_list=<group_NAME> -A <group_NAME> -l nodes=f015:ppn=32 <your script>

2 entire fatnodes, 32 CPUs each, memory of all nodes => 1500 GB RAM)

$ qsub -W group_list=<group_NAME> -A <group_NAME> -l nodes=2:ppn=32:fatnode,mem=1500gb <your script>

Submitting jobs to 28-CPU nodes

The dual-processor, 14 core Intel E5-2683 v3 (28 CPU cores total) we define to have a node property of thinnode (nodes cn001-cn540).You could submit a batch job like in these examples::2 entire thinnodes28 CPUs each, total 56 CPU cores)

$ qsub -W group_list=<group_NAME> -A <group_NAME> -l nodes=2:ppn=28:thinnode <your script>

Explicitly the cn038 node, 28 CPU cores

$ qsub -W group_list=<group_NAME> -A <group_NAME> -l nodes=cn038:ppn=28 <your script>

Submitting 1-CPU jobs

You could submit a batch job like in this example:

$ qsub -W group_list=<group_NAME> -A <group_NAME> -l nodes=1:ppn=1 <your script>

Running parallel jobs using MPI

#!/bin/sh
### Note: No commands may be executed until after the #PBS lines
### Account information
#PBS -W group_list=pr_12345 -A pr_12345
### Job name (comment out the next line to get the name of the script used as the job name)
#PBS -N test
### Output files (comment out the next 2 lines to get the job name used instead)
#PBS -e test.err
#PBS -o test.log
### Only send mail when job is aborted or terminates abnormally
#PBS -m n
### Number of nodes, request 196 cores from 7 nodes
#PBS -l nodes=7:ppn=28
### Requesting time - 720 hours
#PBS -l walltime=720:00:00

### Here follows the user commands:
# Go to the directory from where the job was submitted (initial directory is $HOME)
echo Working directory is $PBS_O_WORKDIR
cd $PBS_O_WORKDIR
# NPROCS will be set to 196, not sure if it used here for anything.
NPROCS=`wc -l < $PBS_NODEFILE`
echo This job has allocated $NPROCS nodes
 
module load moab torque openmpi/gcc/64/1.10.2 gromacs/5.1.2-plumed

export OMP_NUM_THREADS=1
# Using 192 cores for MPI threads leaving 4 cores for overhead, '--mca btl_tcp_if_include ib0' forces InfiniBand interconnect for improved latency
mpirun -np 192 $mdrun -s gmx5_double.tpr -plumed plumed2_path_re.dat -deffnm md-DTU -dlb yes -cpi md-DTU -append --mca btl_tcp_if_include ib0


In order to optimize performance, the queuing system is configured to place jobs on nodes connected to the same InfiniBand switch (30 nodes per switch) if possible.


To get nodes close to each other, use procs=<number_of_procs> and leave out node= and ppn=.To avoid interference with other jobs, procs= should be a multiple of cores per node (ie. 28 for mpinode).

Job Arrays

Submitting multiple identical jobs can be done using job arrays. Job arrays can be created by using the -t option in the qsub submission script. The -t option allows many copies of the same script to be submitted at once. Additional information about -t option can be found in the qsub command reference. Moreover, PBS_ARRAYID environmental variable allows to differentiate the different jobs in the array. The amount of resources required in the qsub submission script is the amount of resources that each job will get.
For instance adding the line:

  #PBS -t 0-14%5

in the qsub script will cause running the job 15 times with not more than 5 actives jobs at any given time.

Please, please, please, use the %# option for limiting the number of active jobs.

PBS_ARRAYID values will run from 0 to 14, as shown below:

 ( perl process.pl dataset${PBS_ARRAYID} )
  
  perl process.pl dataset0
  perl process.pl dataset1
  perl process.pl dataset2
  ….
  perl process.pl dataset14

Jobs in jobs array are run independently and not in any specific order.