Storage Resource Management for Data Grid Applications
A NC Base Program Project
Terascale computing often generates petabytes of data that needs
to be collected and managed. Scientists
accessing the data can be in multiple remote institutions, and the
amount of information processed is only expected to grow.
Such data intensive applications already
overwhelm scientists who spend much of their time managing data,
rather than concentrating on scientific investigations. To improve
access to the data in this mode, data grids are now being developed,
and storage resource management will be an essential part of the
middleware of data grids.
The goal is to enhance the features of storage resource
managers (SRMs) to support dynamic storage management for long lasting
simulation and analysis tasks in a distributed environment.
The objectives of this project are
- Provide dynamic and effective storage resource management
- Develop a Disk Resource Manager to manage a single shared disk cache
- Develop a Storage Resource Manager to manage what data is on each
storage device
- Develop sophisticated pinning capabilities to manage requests to cache files
This project is a collaboration among Lawrence Berkeley National
Laboratory and Fermi National Accelerator Laboratory.
For more info, see:
|