Home

DRM4G is an open platform, based on Gridway, to define, submit, and manage computational jobs. DRM4G is a Python (3.5+) implementation that provides a single point of control for computing resources without installing any intermediate middlewares. As a result, a user is able to run the same job on laptops, desktops, workstations, clusters, supercomputers, and any grid.

Why DRM4G?

• Ready-to-run: The DRM4G bundle can be unpacked and then ran on any on any Linux OS.

• Huge amount of jobs: DRM4G is able to manage around 1,000,000 jobs at the same time.

• Different identities on different resources: DRM4G handles different user accounts on various resources through a single interface.

• One command: In order to make easier to use DRM4G, there is only one command available, which is drm4g.

What is DRM4G's architecture?

Infrastructure layer consists of the following components :

• DRM4G CLI offers users commands to submit, cancel, and monitor jobs and configure resources.

• GridWay core is in charge of job execution and resource brokering. DRM4G takes the most of !GridWay by using its core.

• DRM4G Middleware Access Driver (MAD) gives access to computing resources. In order to do that, there are two kind of components:

  • Resource Manager is responsible for collecting resource information.
  • Communicator provides the authentication type to access them.

• DRM4G Sched is responsible for scheduling jobs.

Getting started

The best way to understand how DRM4G works is following the quickstart guide.

• Installation
• Tutorial
• Resource Configuration
• Job Description
• DRM4G CLI
• DRM4G Python API
• FAQ and common mistakes
• Video from presentation given by C. Blanco at HPCKP'15
• Job life-cycle and job templates in GridWay

Contributing

To make it easier and more accessible for anyone to play around with the DRM4G we have documented how to contribute to this project.