Uppsala Multidisciplinary Center for Advanced Computational Science

Irma User Guide

This is the official users guide to Irma, a high performance computer cluster at UPPMAX. Guides for the other systems at UPPMAX can be found here.

System information

See the Irma presentation page for information about the hardward, and the OS user guide and installed software user guide for details about OS, compilers and installed software.

You will probably have good use of the following commands:

  • uquota - telling you about your file system usage.
  • projinfo - telling you about the CPU hour usage of your projects.
  • jobinfo - telling you about running and waiting jobs on milou.
  • projmembers - telling you about project memberships.
  • projsummary [project id] - summarizes some useful information about projects (the script needs some updates though)

Accounts and log in

All access to this system is done via secure shell (a.k.a SSH) interactive login to the login node, using the domain name irma.uppmax.uu.se if you're an UPPNEX user.

To get a user account, please visit the Getting Started page.

How to set up 2 factor authentication

Access to Irma requires a two factor authentication login. To set up this do:

  1. Go to https://suprintegration.uppmax.uu.se/bootstrapotp/.
  2. You should be sent to SUPR, in case you are not logged in already, log in to SUPR.
  3. Acknowledge to SUPR that they may tell UPPMAX who you are.
  4. Scan the QR-code with the application of your choice in your smart phone, e.g. Google Authenticator from Google Inc. Other alternatives are Duo Security Mobile or Authy.
  5. Your application will give you a code, enter this code on the same webpage.
  6. Now you should be set up to use 2 factor authentication on Irma. It will take some time before your new second factor is imported to irma. You should get a mail within a few minutes notifying you of the newly registered token and information about when it will be activated.

Log in

First, use ssh as usual when connecting to any UPPMAX resource:

ssh -AY user@irma.uppmax.uu.se

After entering your password you will be asked:
Please enter your second factor:

Start your application in your smart phone and enter the code you get.

The 2 factor authentication you have set up will be active for 10 minutes. If you log in again during this time you will not be asked for a second factor. This is primarily intended to be useful for usage with rsync, sftp, scp and other tools that use ssh for communications and do not handle the interactive second factor login well.

For questions concerning accounts and access to Irma, please contact UPPMAX support.

Note that the machine you arrive at when logged in is only a so called login node, where you can do various smaller tasks. We have some limits in place that restricts your usage. For larger tasks you should use our batch system that pushes your jobs onto other machines within the cluster.
 

Using the batch system

To allow a fair and efficient usage of the system we use a resource manager to coordinate user demands. On Irma we use the SLURM software.

Read more about SLURM att UPPMAX.

Some Limits

  • There is a job walltime limit of ten days (240 hours).
  • We restrict each user to at most 5000 running and waiting jobs in total.
  • Each project has a 30 days running allocation of CPU hours. We do not forbid running jobs after the allocation is overdrafted, but instead allow to submit jobs with a very low queue priority, so that you may be able to run your jobs anyway, if a sufficient number of nodes happens to be free on the system.
  • Very wide jobs will only be started within a maintenance window (just before the maintenance window or at the end of the maintenance window). These are planned for the first Wednesday of each month. On Irma a "very wide" job asks for a third of the cluster (67 nodes) or more.

Convenience Variables

$SNIC_TMP - Path to node-local temporary disk space

The $SNIC_TMP variable contains the path to a node-local temporary file directory that you can use when running your jobs, in order to get maxiumum disk performance (since the disks are local to the current compute node). This directory will be automatically created on your (first) compute node before the job starts and automatically deleted when the job has finished.

The path specified in $SNIC_TMP is equal to the path: /scratch/$SLURM_JOB_ID, where the job variable $SLURM_JOB_ID contains the unique job identifier of your job.

WARNING: Please note, that in your "core" (see below) jobs, if you write data in the /scratch directory but outside of the /scratch/$SLURM_JOB_ID directory, your data may be automatically deleteted during your job run.
 

File storage and disk space

The main storage for Irma is Lupus and local disk. Read more about Lupus.

At UPPMAX we have a few different kinds of storage areas for files, see Disk Storage User Guide for more information and recommended use.


Message Passing using MPI

There are currently two mpi implementations installed. This are openMPI and Intelmpi. The module to use are called openmpi or intelmpi. For more information about the implementation of MPI, see http://www.open-mpi.org or https://software.intel.com/en-us/intel-parallel-studio-xe.