High-Throughput Computation on the Open Science Grid, Internet2 Tech Exchange 2018
October 15, 2018
1:00 pm - 5:00 pm
Instructors: Christina Koch, Mats Rynge
General Information
The Open Science Grid provides a fabric of services to enable distributed, high-throughput computing capabilities across the US. In general, OSG is organized into VOs (Virtual Organizations) around large experiments, but individual PIs and groups too small for the VO model can use the hosted services provided by OSG Connect.
The format of this tutorial is a mix of lecture and hands-on exercises, so please bring your laptop and make sure you have an SSH client installed.
The goal of this session is to learn how to run and scale up workloads, manage your data and also spill over into Amazon cloud resources. Topics to include: Introduction to the OSG; Job Scheduling with HTCondor; Scaling Up Workloads; Managing data
Instructors: Christina Koch, Mats Rynge
Where: Loews Royal Pacific Resort, Orlando, FL.
Requirements: Participants must bring a laptop with a few specific software packages installed (see Setup).
Contact: Please mail user-support@opensciencegrid.org for more information.
Schedule
| 1:00 - 1:25 | Introduction to the Open Science Grid [(Slides)] |
| 1:25 - 2:00 | Job Scheduling with HTCondor |
| 2:00 - 2:30 | Organizing Large-scale Submissions |
| 2:30 - 3:00 | Coffee break |
| 3:00 - 3:30 | Multi-Step Workflows via DAGMan |
| 3:30 - 4:20 | Managing Data for OSG Jobs |
| 4:20 - 4:30 | Wrap up, feedback for the workshop and account signups |
Setup Instructions
Instructions to set up the required software on Linux, Windows and Mac laptops