Transition From ACENET Computing Clusters to New National Systems Has Begun
Users of ACENET’s four main advanced computing clusters (Mahone, Fundy, Placentia and Glooscap) have begun to migrate their data and get set up on one of the new Compute Canada state-of-the art systems. The process will be complete by 31 March 2018, at which time these four clusters will be decommissioned.
The target dates by which users should be prepared to leave each system are as follows:
- Mahone, 15 November 2017
- Fundy, 31 November 2017
- Placentia, 31 January 2018
- Glooscap, 28 February 2018
Some of these transfers involve large files, and the process of installing and testing software on a new cluster can take time, so we’re staggering the dates to make it easier for everyone.
As the target date for each cluster approaches we will communicate with its users, providing instructions and resources for migration. There will be at least one month provided to complete the migration.
However, there is no need to wait! Anyone wishing to begin using the new national clusters immediately is encouraged to do so. Check out our Wiki for further information.
There is also lots of training available on using the new Cedar and Graham clusters. Just refer to our training page.
Support throughout and following the transition process will be handled via firstname.lastname@example.org
While this new national infrastructure is not located in Atlantic Canada, ACENET will continue to be the primary support organization for research groups in Atlantic Canada, providing training, research consulting, and troubleshooting. Reach out to your local team, or contact us at email@example.com
Visit the News page for a full archive of news articles
Visit the Events page for a full list of upcoming Events
This workshop combines two introductory sessions.
During the first part of the workshop, participants will learn how to use shell scripting to exercise the power of the command line. Shell scripting helps you save time, automate file management tasks, and better use Linux. The session will teach you how to name, locate and set permissions for executable files, taking input and producing output. Learn about job scripts, shell variables and looping commands.
The second part of the session will teach participants how to use Compute Canada’s queuing environment on the new national systems (Cedar and Graham), using the job scheduler Slurm. Learn how the scheduler works, how it allocates jobs, what are reasonable requests to minimize wait time, how to make the best use of the resources to be more efficient, how to get more throughput, how to get more jobs running at the same time, and how to troubleshoot and deal with crashes.
This workshop is designed for either new HPC users who are familiar with working in a Linux environment, but have not had experience with shell scripting or using Slurm to submit jobs to HPC clusters, or, for experienced users transitioning to Slurm or seeking to get more out of shell scripting and the scheduler.
In order to maximize benefits from the session, participants are strongly encouraged to have a Compute Canada/ACENET account and to bring a laptop to do the exercises.