Frank Dabek
M. Frans Kaashoek
David Karger
Ion Stoica
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.
- 1.Akamai Technologies, Inc. http://www.akamai.com/, 2001. Cambridge, MA.]]Google Scholar
- 2.ANDERSEN, n ., BALAKRISHNAN, H., KAASHOEK, M. F., AND MORRIS, R. Resilient overlay networks. In Proceedings of the 18th ACM Symposium on Operating Systems Principles (Oct. 2001).]] Google ScholarDigital Library
- 3.CHANKHUNTHOD, A., DANZIG, P., NEERDAELS, C., SCHWARTZ, M., AND WORRELL, K. k hierarchical lntemet object cache. In Proc. Usenix Technical Conference (Jan. 1996), pp. 153-163.]] Google ScholarDigital Library
- 4.CHAUM, D. Untraceable electronic mail, return addresses, and digital pseudonyms. Communications of the ACM 24, 2 (Feb. 1981), 84-88.]] Google ScholarDigital Library
- 5.CLARKE, I. A distributed decentralised information storage and retrieval system. Master's thesis, University of Edinburgh, 1999.]]Google Scholar
- 6.CLARKE, 1., SANDBERG, O., WILEY, B., AND HONG, T. Freenet: A distributed anonymous information storage and retrieval system. In Proceedings of the Workshop on Design Issues in Anonymity and Unobservability (July 2000), pp. 46-66.]] Google ScholarDigital Library
- 7.DINGLEDINE, R., FREEDMAN, i ., AND MOLNAR, D. The Free Haven project: Distributed anonymous storage service. In Proceedings of the Workshop on Design Issues in Anonymity and Unobservability (July 2000), pp. 67-95.]] Google ScholarDigital Library
- 8.FAN, L., CAO, P., ALMEIDA, J., AND BRODER, A. Summary cache: a scalable wide-area web-cache sharing protocol. Tech. Rep. 1361, Computer Science Department, University of Wisconsin, Madison, Feb. 1998.]]Google ScholarDigital Library
- 9.FU, K., KAASHOEK, i . F., AND MAZIERES, D. Fast and secure distributed read-only file system. In Proceedings of the 4th USENIX Symposium on Operating Systems Design and Implementation (OSDI) (October 2000), pp. 181-196.]] Google ScholarDigital Library
- 10.GADDE, S., CHASE, J., AND RABINOVICH, i . A taste of crispy squid. In Workshop on lnternet Server Performance (June 1998), pp. 129-136.]]Google Scholar
- 11.Gnutella website, http://gnutella.wego.com.]]Google Scholar
- 12.KARGER, D., LEHMAN, E., LEIGHTON, T., LEVINE, i ,, LEWIN, n., AND PANIGRAHY, R. Consistent hashing and random trees: Distributed caching protocols for relieving hot spots on the world wide web. In Proceedings of the 29th Annual ACM Symposium on Theory of Computing (May 1997), pp. 654-663.]] Google ScholarDigital Library
- 13.KUBIATOWICZ, J., BINDEL, D., CHEN, Y., CZERWINSKI, S., EATON, P., GEELS, D,, GUMMADI, R., RHEA, S., WEATHERSPOON, I-l., WEIMER, W., WELLS, C.. AND ZHAO, B. Oceanstnre: An architecture for global-scale persistent storage, in Praceeedings of the Ninth international Conference on Architectural Support for Frograraming Languages and Operating Systems (ASPLOS) (November 2000), pp. 190-201.]] Google ScholarDigital Library
- 14.LEWlN, D. Consistent hashing and random aces: Algorithms for caching in distributed networks. Master's thesis, MIT, 1998.]]Google Scholar
- 15.MALPANI, R., LURCH, J., AND BERGER, D. Making world wide web caching servers cooperate. In Fourth International World Wide Web Conference (1995), pp. 107-110.]]Google Scholar
- 16.MAZIERES, D. A toolkit for user-level file systems. In Proc. Usenix Technical Conference (June 2001), pp. 261-274.]] Google ScholarDigital Library
- 17.MAZlERES, D., KAMINSKY, M., KAASHOEK, M. F., AND WITCHEL, E. Separating key management from file system security. In Proceedings of the 17th ACM Symposium on Operating Systems Principles (SOSP) (Dee. 1999), pp. 124-139.]] Google ScholarDigital Library
- 18.MERKLE, R. C. A digital signature based on a conventional encryptioa function. In Advances in Cryptolagy--CRYPTO '87 (Berlin, 1987), C. Pomerance, Ed, vol. 293 of Lecture Notes in Computer Science, Springer-Vedag, pp. 369-378.]] Google ScholarDigital Library
- 19.Mojo nation documentation, http:l/www.mojonafion.neVducsL]]Google Scholar
- 20.Napster. http:/lwww.napster com.]]Google Scholar
- 21.NO, T. S. E., STOICA, I., AND ZHAN6, H. A waypoint service approach to connect heterogeneous internet address spaces, tn Prec. Usenix Technical Conference (June 2001), pp. 319-332.]] Google ScholarDigital Library
- 22.Ohaha. http://www., ohaha, co:a/a,,s igu. him1, as of June 17, 2001, the Ohaha application is no longer available.]]Google Scholar
- 23.ORAM, A., Ed. Peer-to-Peer: Harnessing the Power of Disruptive Computation. O'Reilly & Associates, 2001.]] Google ScholarDigital Library
- 24.PLAXTON, C., RAJARAMAN, R., AND RICHA. A. Accessing nearby copies of replicated objects in a dislxibuted environment, in Proceedings of the ACM SPAA (June 1997), pp. 311-320.]] Google ScholarDigital Library
- 25.RABId, M. Efficient dispersal of information for security, load balancing, and fault tolerance. Journal of the ACM 36, 2 (1989), 335-348.]] Google ScholarDigital Library
- 26.RATNASAMY, S., FRANOS, P., HANDLE'C, M., KARP, R., AND SIENKER, S. A sealable content-addressable network. In Proc_ ACM SUIGCOMM (San Diego, 2001).]] Google ScholarDigital Library
- 27.REITER, M., AND RUBIN, A. Crowds: Anonymity for web transactions. ACM Transactions on Information and System Security 1, 1 (Nov. 1998), 66--92,]] Google ScholarDigital Library
- 28.ROWSTRON, A., AND DRUSCrtEL, P. Pastry: Scalable, distributed object location and muting for large-scale peer-to-peer systems In Proceedings of the 18th IFIP/ACM International Conference on Distributed Systems Platforms (MMdleware 2001) (Nov. 2001).]] Google ScholarDigital Library
- 29.ROWSTRON, A., AND DRUSCHEL, P. Storage management and caching in PAST, a large-scale, persistent peer-to-peer storage utility. In Proceedings of the lgth ACM Symposium on Operating Systems Principles (Oct. 2001).]] Google ScholarDigital Library
- 30.SHERMAN, A., KARGER, D ., BERKHEIMIER, A., BOGSTAD, B., DHANIDINA, R., IWAMOTO, K., KIM, B., MATKINS, L., AND YERUSHALMI, Y. Web caeMng with consistent hashing. Computer Neavorks 31, 11-16 (May 1999), 1203-1213.]] Google ScholarDigital Library
- 31.STOICA, I., MORRIS, R., KARGER, D., KAASHOEK. M, F., AND BALAKR1SHNAN, H. Chord: A scalable peer-to-peer lookup service for internet applications. In Proc. ACM S1GCOMM (San Diego, 2001).]] Google ScholarDigital Library
- 32.STOICA, I., MORRIS, R., KARGER, D., KAASHOEK, M. F., AND BALAKRISHNAN, H. Chord: A scalable peer-to-peer lookup service for interact applications. Tech. Rep. TR-819, MIT, Cambridge, MA, March 2001.]]Google Scholar
- 33.TYAN, T. A case study of server selection. Master's thesis, MtT, Sept. 2001.]]Google Scholar
- 34.WALDMAN, M., ROBIN, A., AND CRANOR, L. F. Publius: A robust, tamper-evident, censorship-resistant, web publishing system. In Proc. 9th USENIX Security Symposium (August 2000), pp. 59-72.]] Google ScholarDigital Library
- 35.ZHAO, B., KUBIATOW}CZ, J., AND JOSEPH, A. Tapestry; An inflastxucture for fatflt-tolerant wide-area location and routing. Teeh. Rep. UCB/CSD-01-114I, Computer Science Division, U, C. Berkeley, Apr. 2001.]] Google ScholarDigital Library
Index Terms
- Wide-area cooperative storage with CFS
Recommendations
Wide-area cooperative storage with CFS
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 ...
CFS: A Distributed File System for Large Scale Container Platforms
SIGMOD '19: Proceedings of the 2019 International Conference on Management of DataWe propose CFS, a distributed file system for large scale container platforms. CFS supports both sequential and random file accesses with optimized storage for both large files and small files, and adopts different replication protocols for different ...
Comments