Versions Compared

Key

  • This line was added.
  • This line was removed.
  • Formatting was changed.
Comment: Change title to reflect page content better

Axon is a computer cluster where a scheduler , in this case Slurm, program is used to submit compute tasks, called jobs, to one or more nodes in the cluster. Jobs are submitted to the cluster via the a login node (axon.rc.zi.columbia.edu) as show in the example diagram below:

Warning
titleThe login node (axon.rc.zi.columbia.edu) is for job preparation, not computation!

The login node has limited CPU and memory resources, and should only be used for the preparation of batch jobs or to start an interactive session on one of the nodes.  Terminal sessions on axon.rc.zi.columbia.edu have limits enforced by the operating system- you may only use at most 1 GB of RAM and 6 hours worth of CPU time.  Trying to use more resources will not work.  This is to ensure that other researchers using the login node to submit jobs won't have their work disrupted.

...

Using SSH

Secure Shell (SSH) is the software used by Axon to provide you with a terminal interface. To connect to Axon using this software, you must have a command line interface on your personal computer such as Windows Terminal in Windows 10 or Terminal for Macs. Older versions of Windows may require a third-party program such as Putty or MobaXterm.  Once you have a command line interface on your computer, you can use the following command to log in to Axon:

Connecting from inside the Columbia network or on the VPN

The Axon login node can be accessed when you are on the Columbia campus or using the VPN by using command below:

Code Block
languagebash
themeFadeToGrey
titleTo login to the cluster ssh into the login node (replace aa3301 with your uni)
➤ ssh aa3301@axon.rc.zi.columbia.edu
aa3301@axon.rc.zi.columbia.edu's password:
Last login: Fri Dec 27 15:35:33 2019 from adm.rc.zi.columbia.edu
[aa3301@axon ~]$

Connecting from outside the Columbia network

The Axon login node can be accessed anywhere outside the internal Columbia network by using command below:

...