The Andrew File System is a location-transparent distributed tile system that will eventually span more than 5000 workstations at Carnegie Mellon University. Large scale affects performance and complicates system operation. In this paper we present observations of a prototype implementation, motivate changes in the areas of cache validation, server process structure, name translation, and low-level storage representation, and quantitatively demonstrate Andrew’s ability to scale gracefully. We establish the importance of whole-file transfer and caching in Andrew by comparing its perform-ance with that of Sun Microsystem’s NFS tile system. We also show how the aggregation of files into volumes improves the operability of the system.

Caching introduces the overbead and complexity of ensuring consistency, reducing some of its performance benefits. In a distributed system, caching must deal,wit.h the additional complications of communication and host failures. Leases are proposed as a time-based mechanism that provides efficient consistent access to cached data in distributed systems. Non-Byzantine failures affect performance, not correctness, with their effect minimized by short leases. An analytic model and an evaluation for file access in the V system show that leases of short duration provide good performance. The impact of leases on performance grows more significant in systems of lar;ger scale and higher processor performance. 1

A semantic file system is an information storage system that provides flexible associative access to the system's contents by automatically extracting attributes from files with file type specific transducers. Associative access is provided by a conservative extension to existing tree-structured file system protocols, and by protocols that are designed specifically for content based access. Compatibility with existing file system protocols is provided by introducing the concept of a virtual directory. Virtual directory names are interpreted as queries, and thus provide flexible associative access to files and directories in a manner compatible with existing software. Rapid attribute-based access to file system contents is implemented by automatic extraction and indexing of key properties of file system objects. The automatic indexing of files and directories is called "semantic" because user programmable transducers use information about the semantics of updated file system objects to extract the properties for indexing. Experimental results from a semantic file system implementation support the thesis that semantic file systems present a more effective storage abstraction than do traditional tree structured file systems for information sharing and command level programming.

This paper describes a new version of the Network File System (NFS) that supports access to files larger than 4GB and increases sequential write throughput sevenfold when compared to unaccelerated NFS Version 2. NFS Version 3 maintains the stateless server design and simple crash recovery of NFS Version 2, and the philosophy of building a distributed file service from cooperating protocols. We describe the protocol and its implementation, and provide initial performance measurements. We then describe the implementation effort. Finally, we contrast this work with other distributed file systems and discuss future revisions of NFS. 1.

Extensive caching is a key feature of the Echo distributed file system. Echo client machines maintain coherent caches of file and directory data and properties, with write-behind (delayed write-back) of all cached information. Echo specifies ordering constraints on this write-behind, enabling applications to store and maintain consistent data structures in the file system even when crashes or network faults prevent some writes from being completed. In this paper we describe the Echo cache's coherence and ordering semantics, show how they can improve the performance and consistency of applications, and explain how they are implemented. We also discuss the general problem of reliably notifying applications and users when write-behind is lost; we addressed this problem as part of the Echo design but did not find a fully satisfactory solution.

Caching frequently accessed data items on the client side is an effective technique for improving performance in a mobile environment. Classical cache invalidation strategies are not suitable for mobile environments due to frequent disconnections and mobility of the clients. One attractive cache invalidation technique is based on invalidation reports (IRs). However, the IR-based cache invalidation solution has two major drawbacks, which have not been addressed in previous research. First, there is a long query latency associated with this solution since a client cannot answer the query until the next IR interval. Second, when the server updates a hot data item, all clients have to query the server and get the data from the server separately, which wastes a large amount of bandwidth. In this paper, we propose an IR-based cache invalidation algorithm, which can significantly reduce the query latency and efficiently utilize the broadcast bandwidth. Detailed analytical analysis and simulation experiments are carried out to evaluate the proposed methodology. Compared to previous IR-based schemes, our scheme can significantly improve the throughput and reduce the query latency, the number of uplink request, and the broadcast bandwidth requirements.

JetFile is a file system designed with multicast as its distribution mechanism. The goal is to support a large number of clients in an environment such as the Internet where hosts are attached to both high and low speed networks, sometimes over long distances. JetFile is designed for reduced reliance on servers by allowing client-to-client updates using scalable reliable multicast. Clients on high speed networks prefetch large numbers of files. On low speed networks such as wireless, special caching policies are used to decrease file access latency. The prototype implementation of JetFile is on the JetStream gigabit local area network which provides hardware support for many multicast addresses. The multicast Internet backbone (Mbone) is the wide area testbed for JetFile. 1 Introduction To achieve scalability in a wide area network environment, the next generation of distributed file systems need a new paradigm of communication. The prevailing mode of communication for current distrib...

The dissertation presents the issues addressed in the design of Ficus, a large scale wide area distributed file system currently operational on a modest scale at UCLA. Key aspects of providing such a service include toleration of partial operation in virtually all areas; support for large scale, optimistic data replication; and a flexible, extensible modular design. Ficus incorporates a "stackable layers" modular architecture and full support for optimistic replication. Replication is provided by a pair of layers operating in concert above a traditional filing service. A "volume" abstraction and on-the-fly volume "grafting" mechanism are used to manage the large scale file name space. The replication service uses a f...

The Network File System (NFS) Version 4 is a new distributed file system similar to previous versions of NFS in its straightforward design, simplified error recovery, and independence of transport protocols and operating systems for file access in a heterogeneous network. Unlike earlier versions of NFS, the new protocol integrates file locking, strong security, operation coalescing, and delegation capabilities to enhance client performance for narrow data sharing applications on high-bandwidth networks. Locking and delegation make NFS stateful, but simplicity of design is retained through well-defined recovery semantics in the face of client and server failures and network partitions. This paper describes the new features of the protocol, focusing on the security enhancements, integrated locking support, changes to fully support Windows file sharing semantics, support for high performance data sharing, and the design points that enhance performance on the Internet.

RPC latencies and other network-related delays can frustrate mobile users of a distributed file system. Disconnected operation helps, but fails to use networking opportunities to their full advantage. In this paper we describe partially connected operation, an extension of disconnected operation that resolves cache misses and preserves client cache consistency, but does not incur the write latencies of a fully connected client. Benchmarks of partially connected mode over a slow network indicate overall system performance comparable to fully connected operation over Ethernet.