Cluster Basics


Biocluster is a collection of machines managed and linked together to allow for computational and other complex problem sets to be submitted, and to have the results returned in a timely fashion. The way we achieve this is a queuing and scheduling system that places jobs on particular nodes. A node is a single system part that is part of the larger collection. In our case, there are 34 nodes. Of those, 32 of them have 16 GB of RAM and 8 CPU cores. Two of those nodes have 48 CPU cores and 64 GB of RAM. A glossary of terms will be provided at the end to help with any terms you are unfamiliar with.

Getting Connected

This guide will walk you through connecting to biocluster using the Secure Shell protocol, SSH, from your workstation or laptop.


Download and Install PuTTY

Visit and download the Installer. Once downloaded, Run the installer and complete the installation.

Using PuTTY To Connect

Launch PuTTY

Putty can be found by going to Start > All Programs > PuTTY > PuTTY.


Connecting to Biocluster

Once you have launched PuTTY, fill in the Host Name box with and then click Open.


You may get a PuTTY Security Alert dialog box that pops up. This is normal and should only happen the first time you connect to biocluster from that computer. It is safe to click Yes.


You will then be presented with a screen that asks for your username, enter the username you were given by Dr. Girke or the systems administrator. Press enter and then you will be asked for your password, use the password you were given with the username.


If all goes well, you should end up with a screen that looks like this:




ssh - Used on Mac OS X and Linux to connect to other systems.


job - A job is a task that is submitted to the queue for processing.

SSH - A secure protocol for establishing interactive sessions with systems.