Massively Scalable File Storage (2009)

With the fast evolution of the Internet, the explosion of data volume and growing online services, massively scalable file storage is a reality today. We all use P2P applications which finally use workstation private storage space to enable an almost infinite space. Compliance and Archiving put also a high pressure on file storage and many solutions use innovative approaches developed recently, some research work was done around RAIN architecture. High Performance applications must run and use high performance file storage infrastructure and many proprietary developments were made to address these needs. Some standard work was also done by many vendors to propose some new parallel mode such as pNFS. This session covers only the high-end part of network file storage with high performance, reliability and huge capacity and presents P2P, CAS, Distributed, Parallel and Cloud file storage with important number of servers and clients such as Google FS, Apache project named Hadoop, PVFS, Lustre, pNFS and a few proprietary ones to illustrate industry answers.

Learning Objectives

Introduces and review all high-end network file storage technologies to help better understand vendors’ solutions and standards challenges.
Help understand each design, advantages and drawback to align with applications needs.
Participate to the education of the market to simplify technology adoption.