ABSTRACT
Network Transparency in Wide Area Collaborations
Jiaying Zhang
Ph.D. Dissertation, University of Michigan, Ann Arbor, May 2007.
The advent of wide-area high-speed networks provides the framework for deploying large scale applications. Concurrently, recent years have seen an increasing demand for global collaborations in scientific studies, spanning disciplines from high-energy physics, to climatology, to genomics. Applications in these fields demand intensive use of computational resources far beyond the scope of a single organization, and require access to massive amounts of data. This introduces the need for scalable, efficient, and reliable data access and management schemes.
To meet availability, performance, and scalability requirements, distributed services naturally turn to replication and file service is no exception. While the concept of file replication is not new, existing solutions either forsake read/write replication totally or weaken consistency guarantees. They fail to satisfy the requirements of global scientific collaborations, in which users want to use widely distributed computation and storage resources as though they were using them locally.
The rapid evolution of wide-area collaborations calls for a mutable replicated file system that supports consistent data access. However, when designing such a system, we must also consider the tradeoffs among consistency, performance, and availability. Most scientific applications are read dominant, so a file system cannot become widely deployed if it supports mutable replication at the cost of impairing normal read performance. Similarly, support for strong consistency guarantees should not slow down applications for which weaker consistency semantics suffice, otherwise, those applications will not choose to employ the system.
This dissertation describes a replicated file system designed to meet the needs of global collaborations. We build a naming scheme that supports a global name space and location independent naming, which facilitates data sharing, distribution, and management. We develop a replication protocol that supports mutable replication with strong consistency guarantees. We implement our design in NFSv4, the new Internet distributed file system protocol, and evaluate the performance of the system with scientific applications. These studies support my thesis that a replicated file system framework addressing the data access and storage requirements of the emerging global collaborations is feasible and practical.
