University Adapts to Computational Computing with eQUEUE
For many years, Washington University in St. Louis operated a dedicated Linux Lab for use by professors and students. In recent years, Mark Bober, Manager of Computational Services at the School of Engineering, said professors have shifted their teaching style with respect to computing.
As a result, students are no longer sitting down and using desktop computers as they did previously. Now the focus for professors – and students – is on parallel computing. Bober said he confirmed this new trend.
“We started off putting a job scheduler on the desktops in the lab, but it was hard to balance the desktop needs with the computing needs,” Bober said. “At a physical desktop, any user could sit down and interrupt running jobs without warning, or a job could hit a desktop a student was using and ruin their experience. The need to avoid those problems made the experience as a whole less than satisifying.”
Just as Bober and his team were confronting this change in Linux lab usage, he learned about the eQUEUE web-based job submission software developed by Advanced Clustering Technologies.
“With eQUEUE we can make the shift to a job-based computational model, just like we use in our research clusters, without giving up the capability to provide a Linux desktop experience.” Bober said. “We’ve also seen a growth in things like auto-grading of code assignments from the CSE department, and we can now spread those out into the job queue rather than having them threaten to overwhelm our SSH access server.”
Washington University in St. Louis put the cluster hardware and eQUEUE software in place in April 2015. Bober said he and his team will have a pair of classes using the system this summer and will make it available to everyone in the fall.
“One of the big wins for the school as a whole is that we can now provide a Linux desktop environment in any of our computer labs or classrooms – not just a single lab. As a result, we’ll end up being able to combine the old Linux Lab space together with another lab, and free up physical space elsewhere. A project that ends with making space available for other uses at a university is hard to find, and eQUEUE is an incredibly economical way to make that happen.”
We want to thank Mark Bober, Manager of Computational Services at Washington University in St. Louis, for sharing his experience with eQUEUE.
Bring More Users to Your Cluster with Our eQUEUE Job Submission Software
Your users won’t need to learn a single line of code to start adding their jobs to your cluster. Find out how eQUEUE can help you manage your cluster and drive more usage.
Learn how eQUEUE helps with:
- submitting jobs
- remote visualization
- analytics and reporting
- job management
- job history and insights
- accessing files
You might also want to learn more about new features being added to eQUEUE.
- Case Study: UTFR Runs CFD Simulations in the Cloud to Optimize Formula SAE Car Design
- Case Study: Weather Forecasting in the Cloud
- Building an HPC Solution with Flexibility to Meet Future Needs
- Cost and Performance Enhance Research Efforts
- Closing the Gap On Memory Performance For Development Of Genetic Data Analysis Software
- The Virtual Campus: One of the Nation’s Largest Passive Stereoscopic Tiled Wall Displays
- Apex Clusters Increase Efficiency and Save Money!
- University Adapts to Computational Computing with eQUEUE
- Cluster Speeds Molecular Dynamics Research with NVIDIA GPUs
- Enabling Computational Research for the ‘Missing Middle’