Achieving Efficient Pathname LOOKUP in File Server Group

Abstract

With the increasing growth of Internet users and the Web contents, it has led to much attention on scalability and availability of file system. Hence the ways to improve the reliability and availability of system, to achieve the expected reduction in operational expenses and to reduce the operations of management of system have become essential issues. In FSG system, it improved the reliability of file system through replication to handle the effects of failures. An efficient consistency control protocol is previously proposed to ensure the consistency among replicas. In this paper, we leveraged the concept of intermediate file handle to cover the heterogeneity of file system and designed a mechanism, named Multi-component LOOKUP to solve the inefficiency problem of full pathname LOOKUP, to reduce the number of RPC requests going across the network and to allow a client to resolve a full path name in one operation. Above all, simplicity is our main design consideration.

An Overview of File Server Group in Distributed Systems

“…So there is no need that all file servers in the group must advertise their state periodically as in [1]. Our proposed idea is efficient reducing network bandwidth for such advertisements.…”

“…It means that before accessing a specific file server, AS will authenticate the client and will check for the file requested by the client. If the requested file is there on any file server, mounting process as defined in [1], [6], will take hold, otherwise connection terminate.…”

“…In Client Server Scenario the following steps are taking hold when a client wants to read data from a specific file server. This solution was proposed in [1], [3], [5].…”