Notre Dame Condor Pool

The University of Notre Dame has a Condor pool which harnesses the idle computational cycles from workstations and servers all over campus to run batch jobs. Condor provides access to over 20,000 cores. The Condor pool is maintained by the Notre Dame Cooperative Computing Lab (CCL) and CRC; most of the information in this article is taken directly from the CCL website

Visual Status of the ND Condor Pool

ND Condor Utilization Matrix

Online Short Course

Short Course In Data Centric Computing

About Condor

Condor is a distributed batch computing system used at many institutions around the world. Condor allows many users to share their computing resources, thus giving everyone access to more computing power than any one person could afford to buy. In particular, Condor is good at harnessing idle cycles from under-used servers.

Users that submit jobs to Condor can specify their own requirements on what machines to use. You can require the use of one particular machine, or any from a particular cluster, or any with a certain amount of memory or processor type. Of course, if you are borrowing machines owned by other people, then you must accept the possibility that some jobs may be kicked off and must run elsewhere.

For more information about Condor, please visit the Condor project page at:

Getting Started With Condor at Notre Dame

Log into to submit jobs.

To submit a batch job to Condor, you must create a submission file and then run the condor_submit command. Try creating this sample submit file in /tmp/YOURNAME/test.submit.

universe = vanilla
executable = /bin/echo
arguments = hello condor
output = test.output
should_transfer_files = yes
when_to_transfer_output = on_exit
log = test.logfile

Now, to submit the job to Condor, execute:

cd /tmp/YOURNAME
condor_submit test.submit
Submitting job(s)...
1 job(s) submitted to cluster 2.

Once the job is submitted, you can use condor_q to look at the status of the jobs in your queue. If you run condor_q quickly enough, you will see your job idle:

-- Submitter: : <> :
   2.0   dthain          8/26 17:21   0+00:00:00 I  0   0.0  echo hello world

If you job remains in state I 'idle' for a significant amount of time you should check to see why it has not started. There is most likely a problem matching your request with an available resource which will be shown with the following command.

condor_q  yourjobnumberhere  -better-analyze

The command below shows the relative priority of everyone who has recently run jobs. Those with lower priority numbers have their waiting jobs start before others.


If you decide to cancel a job, use condor_rm and the job id:

condor_rm 2.0
Job 2.0 marked for removal.

Note about email: Despite what the Condor manual says, you will not receive email when a job is complete. This feature has been disabled at Notre Dame due to our email security configuration.

Important note about AFS

In the example above, the submit file and all of the job's details were stored in /tmp/YOURNAME on your local disk. Condor simply moved the necessary files back and forth in order to run your jobs. If instead you store your data files in AFS (i.e. your home directory), Condor cannot access them because it will not have your AFS token or Kerberos ticket.

If you want Condor to be able to read any data out of AFS, you must change the ACLs on the necessary directories to allow the security group nd_campus to read the data. Note that this will allow anyone with a valid account to read the data within the directory.

Here's how:

fs setacl ~/my/data/directory nd_campus read

If you want Condor to be able to write to AFS, you must change the ACLs to the following:

fs setacl ~/my/data/directory nd_campus rlidw

Because AFS permissions are hierarchical, in both of these examples nd_campus must have at least lookup 'l' permission in the destination directory's parent directories. For example,

fs setacl ~/my nd_campus l
fs setacl ~/my/data nd_campus l

If there are several directories, the find command may be used to set ACLs recursively:

find ~/my -type d -exec fs setacl {} nd_campus read \; 

Submitting Large Numbers of Jobs

Because you will certainly want to run many jobs at once via Condor, you can easily modify your submit file to run a program with tens or hundreds of variations. Change the queue command to queue several jobs at once, and the $(PROCESS) macro to modify the parameters with the job number.

universe = vanilla
executable = /bin/echo
arguments = hello $(PROCESS)
output = test.output.$(PROCESS)
error = test.error.$(PROCESS)
should_transfer_files = yes
when_to_transfer_output = on_exit
log = test.logfile
queue 10

Now, when you run condor_submit, you should see something like this:

condor_submit test.submit
Submitting job(s)..........
10 job(s) submitted to cluster 9.

Note in this case that "cluster" means "a bunch of jobs", where each job is named 9.0, 9.1, 9.2, and so forth. In this next example, condor_q shows that cluster 9 is halfway complete, with job 9.5 currently running.

-- Submitter: : <> :
   9.5   dthain          8/26 17:46   0+00:00:01 R  0   0.0  echo hello 5
   9.6   dthain          8/26 17:46   0+00:00:00 I  0   0.0  echo hello 6
   9.7   dthain          8/26 17:46   0+00:00:00 I  0   0.0  echo hello 7
   9.8   dthain          8/26 17:46   0+00:00:00 I  0   0.0  echo hello 8
   9.9   dthain          8/26 17:46   0+00:00:00 I  0   0.0  echo hello 9

To Submit Multicore SMP jobs to the ND Condor Pool

The condor pool is configured to enable dynamic slots (new feature in recent releases). Therefore, if you want to submit multi-threaded or multicore SMP Condor jobs (e.g. using OpenMP), you can add below lines in your Condor job script:


environment = OMP_NUM_THREADS=4;LD_LIBRARY_PATH=/opt/crc/intel/14.0/lib/intel64
request_cpus = 4

For example, if you compile below hellow_world.c:

#include <omp.h>
#include <stdio.h>
#include <stdlib.h>
int main (int argc, char *argv[]) {

int nthreads, tid;

/* Fork a team of threads giving them their own copies of variables */
#pragma omp parallel private(nthreads, tid)

 /* Obtain thread number */
 tid = omp_get_thread_num();
 printf("Hello World from thread = %d\n", tid);

 /* Only master thread does this */
 if (tid == 0) 
  nthreads = omp_get_num_threads();
 printf("Number of threads = %d\n", nthreads);

 } /* All threads join master thread and disband */



icc -openmp hello_world.c -o hello_world.x

and then submit your Condor job script with

executable = hello_world.x

and above options, then you will get an output, for example, like:

 Hello World from thread =            0
 Hello World from thread =            1
 Hello World from thread =            3
 Hello World from thread =            2
 Number of threads =            4

Example of Submitting 10 Matlab jobs through Condor

Following is a Condor submission script template for running Matlab with 4 cores:

universe = vanilla
getenv = true
executable = Path_to_your_executable_file/
output = test.output
error = test.error
request_cpus = 4
should_transfer_files = yes
when_to_transfer_output = on_exit
log = logfile
queue 10

with '':


if [ -r /opt/crc/Modules/current/init/bash ]; then
        source /opt/crc/Modules/current/init/bash

module load matlab

# If needed, specify the location of additional .m files.  Note that Condor must be able to read this directory.
export MATLABPATH=/path/to/your/matlab/files

#  Substitute your ID below to ensure Matlab can write configuration files to a unique directory:
export TMPDIR=/tmp/AFS_ID

# Determine the full path to a matlab version
export MLAB=`which matlab`

${MLAB} -nodisplay -nosplash -nojvm -r "myFunction('$1');exit"

Condor Status

You can view the total number of CPUs currently in the Condor pool here or you can view a list of all the machines in the pool here.

In addition, you can view information about users with jobs currently in the queue here, and you can view a list of all the machines currently running jobs here.

For a full visual status of the Condor pool, please see the Condor Visual Status Page, located here (requires Java).

More information about the status of the Condor pool, including historical data, can be found at the CCL web page, located here.

More Information

For a more in-depth tutorial, please take a look at the full tutorial.

There is much more to Condor. Please read the manual to learn more.

Users and administrators of Condor at Notre Dame are encouraged to subscribe to the condor-discuss mailing list to learn more.