Wide-area cooperative storage with CFS
Top Cited Papers
- 21 October 2001
- proceedings article
- Published by Association for Computing Machinery (ACM)
- Vol. 35 (5) , 202-215
- https://doi.org/10.1145/502034.502054
Abstract
The Cooperative File System (CFS) is a new peer-to-peer read-only storage system that provides provable guarantees for the efficiency, robustness, and load-balance of file storage and retrieval. CFS does this with a completely decentralized architecture that can scale to large systems. CFS servers provide a distributed hash table (DHash) for block storage. CFS clients interpret DHash blocks as a file system. DHash distributes and caches blocks at a fine granularity to achieve load balance, uses replication for robustness, and decreases latency with server selection. DHash finds blocks using the Chord location protocol, which operates in time logarithmic in the number of servers.CFS is implemented using the SFS file system toolkit and runs on Linux, OpenBSD, and FreeBSD. Experience on a globally deployed prototype shows that CFS delivers data to clients as fast as FTP. Controlled tests show that CFS is scalable: with 4,096 servers, looking up a block of data involves contacting only seven servers. The tests also demonstrate nearly perfect robustness and unimpaired performance even when as many as half the servers fail.Keywords
This publication has 14 references indexed in Scilit:
- Pastry: Scalable, Decentralized Object Location, and Routing for Large-Scale Peer-to-Peer SystemsPublished by Springer Nature ,2001
- Resilient overlay networksPublished by Association for Computing Machinery (ACM) ,2001
- A scalable content-addressable networkPublished by Association for Computing Machinery (ACM) ,2001
- ChordPublished by Association for Computing Machinery (ACM) ,2001
- Web caching with consistent hashingComputer Networks, 1999
- CrowdsACM Transactions on Information and System Security, 1998
- Consistent hashing and random treesPublished by Association for Computing Machinery (ACM) ,1997
- Accessing nearby copies of replicated objects in a distributed environmentPublished by Association for Computing Machinery (ACM) ,1997
- Efficient dispersal of information for security, load balancing, and fault toleranceJournal of the ACM, 1989
- Untraceable electronic mail, return addresses, and digital pseudonymsCommunications of the ACM, 1981