Sun Microsystems' autoClient and management of computer farms at BaBar
Modern HEP experiments require immense amounts of computing power. In the BaBar experiment at SLAC, most of it is provided by Solaris SPARC systems. AutoClient, a product of Sun Microsystems, was designed to make setting up and managing large numbers of Solaris systems more straightforward. AutoClient machines keep all file systems, except swap, on a server and employ CacheFS to cache them onto a local disk, which makes them Field Replaceable Units with performance of stand-alone systems. The authors began exploring the technology in Summer 1998, and currently operate online, reconstruction, analysis and console AutoClient farms with the total number of nodes exceeding 400. Although the technology has been available since 1995, it has not been widely used, and the available documentation does not adequately cover many important details of AutoClient installation and management. This paper discusses various aspects of the authors experience with AutoClient, including tips and tricks, performance and maintainability, scalability and server requirements, existing problems and possible future enhancements.
- Research Organization:
- SLAC National Accelerator Lab., Menlo Park, CA (United States)
- Sponsoring Organization:
- USDOE Office of Energy Research (ER) (US)
- DOE Contract Number:
- AC03-76SF00515
- OSTI ID:
- 753297
- Report Number(s):
- SLAC-PUB-8368; TRN: US0001917
- Resource Relation:
- Other Information: PBD: 10 Feb 2000
- Country of Publication:
- United States
- Language:
- English
Similar Records
On the Verge of One Petabyte - the Story Behind the BaBar Database System
Production of BaBar Skimmed Analysis Datasets Using the Grid