Feasibility of a serverless distributed file system deployed on an existing set of desktop PCs
Published 1 June 2000Open access
William J. Bolosky, John R. Douceur, David P. Ely, Marvin Theimer
Citations488
Generate an AI Snapshot to get a quick, structured summary of this paper.
Study Snapshot
ObjectiveStudy objective
MethodsResearch methodology
PopulationPopulation studied
Sample sizeSample sizes
OutcomesStudy outcomes here
ResultsStudy results comes here
LimitationsResearch study limitations comes here
A concise AI-generated summary of the paper will appear here once you click Generate AI Snapshot.
TL;DR
It is concluded that the measured desktop infrastructure would passably support the proposed serverless distributed file system, providing availability on the order of one unfilled file request per user per thousand days.
Abstract
We consider an architecture for a serverless distributed file system that does not assume mutual trust among the client computers. The system provides security, availability, and reliability by distributing multiple encrypted replicas of each file among the client machines. To assess the feasibility of deploying this system on an existing desktop infrastructure, we measure and analyze a large set of client machines in a commercial environment. In particular, we measure and report results on disk usage and content; file activity; and machine uptimes, lifetimes, and loads. We conclude that the measured desktop infrastructure would passably support our proposed system, providing availability on the order of one unfilled file request per user per thousand days.
Keywords
Computer Science
Web caching and Zipf-like distributions: evidence and implications
3,486 Citations1999Lee Breslau, Pei Cao +3 more
This paper investigates the page request distribution seen by Web proxy caches using traces from a variety of sources and considers a simple model where the Web accesses are independent and the reference probability of the documents follows a Zipf-like distribution, suggesting that the various observed properties of hit-ratios and temporal locality are indeed inherent to Web accesse observed by proxies.
ACM SIGMOD RecordA case for redundant arrays of inexpensive disks (RAID)
2,301 Citations1988David A. Patterson, Garth A. Gibson +1 more
A case for redundant arrays of inexpensive disks (RAID)
1,427 Citations1988David A. Patterson, Garth A. Gibson +1 more
Five levels of RAIDs are introduced, giving their relative cost/performance, and a comparison to an IBM 3380 and a Fujitsu Super Eagle is compared.
ACM Transactions on Computer SystemsScale and performance in a distributed file system
1,412 Citations1988John H. Howard, Michael L. Kazar +5 more
This paper examines the consequences of the design decision to transfer whole files between servers and workstations rather than some smaller unit such as records or blocks, as almost all other distributed file systems do, and compares the whole file transfer strategy with that of a block-oriented file system, Sun Microsystems' NFS.
Weighted voting for replicated data
1,323 Citations1979David K. Gifford
The algorithm guarantees serial consistency, admits temporary copies in a natural way by the introduction of copies with no votes, and has been implemented in the context of an application system called Violet.
ACM Transactions on Computer SystemsDisconnected operation in the Coda File System
1,070 Citations1992James J. Kistler, Mahadev Satyanarayanan
This paper shows that disconnected operation is feasible, efficient and usable by describing its design and implementation in the Coda File System by showing that caching of data, now widely used for performance, can also be exploited to improve availability.
IEEE MicroA case for NOW (Networks of Workstations)
797 Citations1995Thomas E. Anderson, David Culler +1 more
This paper identifies three opportunities for NOWs that will benefit end- users: dramatically improving virtual memory and file system performance by using the aggregate DRAM of a NOW as a giant cache for disk, achieving cheap, highly available, and scalable file storage by using redundant arrays of workstation disks, and multiple CPUs for parallel computing.
ACM Transactions on Computer SystemsA fast file system for UNIX
745 Citations1984Marshall Kirk McKusick, William N. Joy +2 more
A reimplementation of the UNIX TM file system is described, which provides substantially higher throughput rates by using more flexible allocation policies that allow better locality of reference and can be adapted to a wide range of peripheral and processor characteristics.
Measurements of a distributed file system
535 Citations1991Mary G. Baker, John H. Hartman +3 more
This work analyzed the user-level file access patterns and caching behavior of the Sprite distributed file system and found that client cache consistency is needed to prevent stale data errors, but that it is not invoked often enough to degrade overall system performance.
ACM Transactions on Computer SystemsCaching in the Sprite network file system
503 Citations1988Michael N. Nelson, Brent Welch +1 more
ACM SIGOPS Operating Systems ReviewA trace-driven analysis of the UNIX 4.2 BSD file system
498 Citations1985John K. Ousterhout, Hervé Da Costa +4 more
The UNIX 4.2 BSD file system was analyzed by recording user-level activity in trace files and writing programs to analyze the traces, which allowed us to deduce the exact ranges of bytes accessed, although the access times were less precise than they would have been if the authors had logged reads and writes.
ACM SIGOPS Operating Systems ReviewServerless network file systems
475 Citations1995Thomas E. Anderson, Michael Dahlin +4 more
NASA Technical Reports Server (NASA)Transparent process migration: Design alternatives and the Sprite implementation
450 CitationsFred Douglis, John K. Ousterhout
Frangipani
380 Citations1997Chandramohan A. Thekkath, Timothy Mann +1 more
Initial measurements indicate that Frangipani has excellent single-server performance and scales well as servers are added, and can be exported to untrusted machines using ordinary network file access protocols.
ACM SIGOPS Operating Systems ReviewThe LOCUS distributed operating system
372 Citations1983Bruce J. Walker, Gerald J. Popek +3 more
Medical Entomology and ZoologyInside Windows NT
305 Citations1992David A. Solomon, Helen Custer
This classic, newly updated guide to Windows NT architecture takes you deep into the core components of Windows NT and gives abundant information, insight, and perspective that you can quickly apply for better design, debugging, performance, and troubleshooting.
ComputerScalable, secure, and highly available distributed file access
276 Citations1990Mahadev Satyanarayanan
Andrew and Coda are distributed Unix file systems that embody many of the recent advances in solving the problem of data sharing in large, physically dispersed workstation environments.
ACM SIGOPS Operating Systems ReviewMachine-independent virtual memory management for paged uniprocessor and multiprocessor architectures
230 Citations1987Richard F. Rashid, Avadis Tevanian +6 more
A large-scale study of file-system contents
215 Citations1999John R. Douceur, William J. Bolosky
It is found that file and directory sizes are fairly consistent across file systems, but file lifetimes vary widely and are significantly affected by the job function of the user.
File system usage in Windows NT 4.0
209 Citations1999Werner Vogels
This paper reports on the usage details of the Windows NT file system architecture, through a detailed comparison with the older traces, through details on the operational characteristics and through a usage analysis of the file system and cache manager.
ACM SIGMETRICS Performance Evaluation ReviewThe interaction of parallel and sequential workloads on a network of workstations
209 Citations1995Remzi H. Arpaci, Andrea C. Dusseau +4 more
Serverless network file systems
198 Citations1995Thomas E. Anderson, Michael Dahlin +4 more
A new paradigm for network file system design, serverless network file systems that utilizes workstations cooperating as peers to provide all file system services to provide better performance and scalability than traditional file systems.
The LOCUS distributed operating system
197 Citations1983Bruce D. Walker, Gerald J. Popek +3 more
The complete system architecture is outlined in this paper, and that experience in its use has been summarized.
Performance EvaluationThe available capacity of a privately owned workstation environment
159 Citations1991Matt W. Mutka, Miron Livny
To understand the profile of station availability, the usage patterns of a cluster of workstations were analyzed and a stochastic model was developed which was based on an analysis of the relative frequency distribution and the correlation of available and non-available interval lengths.
Single Instance Storage in Windows
144 Citations2000William J. Bolosky, Scott Corbin +2 more
The Single Instance Store (SIS), a component within Windows ® 2000 that implements links with the semantics of copies for files stored on a Windows 2000 NTFS volume, is described and briefly presents measurements of a remote install server showing a 58% disk space savings by using SIS.
Software Practice and ExperienceLong Term Distributed File Reference Tracing: Implementation and Experience
86 Citations1996Lily Mummert, Mahadev Satyanarayanan
The design, implementation, and evaluation of DFSTrace and associated tools are presented, and how they have been used are described.
Machine-independent virtual memory management for paged uniprocessor and multiprocessor architectures
68 Citations1987Richard F. Rashid, Avadis Tevanian +6 more
The design and implementation of virtual memory management within the CMU Mach Operating System and the experiences gained by the Mach kernel group in porting that system to a variety of architectures are described.
ACM SIGMETRICS Performance Evaluation ReviewA large-scale study of file-system contents
59 Citations1999John R. Douceur, William J. Bolosky