Filters








18,037 Hits in 4.5 sec

An algorithm, for replicated directories

Dean Daniels, Alfred Z. Spector
1983 Proceedings of the second annual ACM symposium on Principles of distributed computing - PODC '83  
This paper describes a replication algorithm for directory objects based upon Gifford's weighted voting for files.  ...  The algorithm associates a version number with each possible key on every replica and thereby resolves an ambiguity that arises when directory entries are not stored in every replica.  ...  Acknowledgments James Driscoll suggested improvements to our initial dynamic partitioning algorithm that resulted in the algorithm presented in this paper.  ... 
doi:10.1145/800221.806713 dblp:conf/podc/DanielsS83 fatcat:56jbtm7r3rcztexsmh3v5ksgjm

An algorithm for replicated directories

Alfred Z Spector, Dean Daniels
1986 ACM SIGOPS Operating Systems Review  
This paper describes a replication algorithm for directory objects based upon Gifford's weighted voting for files.  ...  The algorithm associates a version number with each possible key on every replica and thereby resolves an ambiguity that arises when directory entries are not stored in every replica.  ...  Acknowledgments James Driscoll suggested improvements to our initial dynamic partitioning algorithm that resulted in the algorithm presented in this paper.  ... 
doi:10.1145/12485.12489 fatcat:n5qq7umybfhjjmm23hri735qfq

An algorithm for replicated directories

Dean Daniels, Alfred Z. Spector
2018
Acknowledgments James Driscoll suggested improvements to our initial dynamic partitioning algorithm that resulted in the algorithm presented in this paper.  ...  These improvements simplified the algorithm and reduced the amount of  ...  While weighted voting is an appealing approach to directory replication, the basic algorithm can not be applied to directories without undesirable concurrency limitations.  ... 
doi:10.1184/r1/6603176.v1 fatcat:5rgopopzhrcf7n4pyirdtcq5km

Brief announcement

Rui Fan, Nancy A. Lynch
2003 Proceedings of the twenty-second annual symposium on Principles of distributed computing - PODC '03  
Data replication is an important technique for improving the reliability and scalability of data services.  ...  Our second lower bound shows this behavior is inherent for the class of selfish atomic replication algorithms.  ...  lynch @ theory.lcs.mit.edu Data replication is an important technique for improving the reliability and scalability of data services.  ... 
doi:10.1145/872035.872085 dblp:conf/podc/FanL03 fatcat:g47c7p7lcfazxgvu6wuxfqdipe

Enhancing Duplicate Collection Detection Through Replica Boundary Discovery [chapter]

Zhigang Zhang, Weijia Jia, Xiaoming Li
2006 Lecture Notes in Computer Science  
Web documents are widely replicated on the Internet. These replicated documents bring potential problems to Web based information systems. So replica detection on the Web is an indispensable task.  ...  ; second, it can identify the boundary of the replicated collections accurately, demonstrating to what extent two collections are replicated.  ...  Conclusions and Future Work In this paper, we propose an intermediate granularity of replication on the Web at the directory level, and present an effective approach to discover the replicated directories  ... 
doi:10.1007/11731139_42 fatcat:uypztzj3jzcthcpje2j6cguh3u

A Dynamic Popularity-Aware Load Balancing Algorithm for Structured P2P Systems [chapter]

Narjes Soltani, Ehsan Mousavi Khaneghah, Mohsen Sharifi, Seyedeh Leili Mirtaheri
2012 Lecture Notes in Computer Science  
It also considers the load transfer time as an important factor in calculating the cost of load balancing. We present the algorithm using node movement and replication mechanisms.  ...  Most existing load balancing algorithms for structured P2Psystems are not proximity-aware, assume uniform distribution of objects in the system and often ignore node heterogeneity.  ...  For the purpose of replication, we use a second hash function called SecHash and also a set of replication directories each called RepDir.  ... 
doi:10.1007/978-3-642-35606-3_9 fatcat:hovrd5r5rzfgjkn7pyodacgefe

A Load Balancing Algorithm Based on Replication and Movement af Data Items for Dynamic Structured P2P Systems

Narjes Soltani, Mohsen Sharifi
2014 International Journal of Peer to Peer Networks  
In this paper we propose a load balancing algorithm that considers the above issues by applying node movement and replication mechanisms while load balancing.  ...  Most existing load balancing algorithms for structured P2P systems are not adaptable to objects' variant loads in different system conditions, assume uniform distribution of objects in the system, and  ...  For the purpose of replication, we use a second hash function called SecHash and also a set of replication directories each called RepDir.  ... 
doi:10.5121/ijp2p.2014.5302 fatcat:puokyrf4bvesjajzlw4hw7jhpu

Efficient Replication of Large Data Objects [chapter]

Rui Fan, Nancy Lynch
2003 Lecture Notes in Computer Science  
We present a new distributed data replication algorithm tailored especially for large-scale read/write data objects such as files.  ...  It is suitable for implementation in WANs as well as LANs. We also present two lower bounds on the costs of data replication.  ...  Conclusions In this paper we presented LDR, an efficient replication algorithm based on separately replicating data and metadata.  ... 
doi:10.1007/978-3-540-39989-6_6 fatcat:7hdusg2igbaevmwhlhznqh5mri

A weighted voting algorithm for replicated directories

Joshua J. Bloch, Dean S. Daniels, Alfred Z. Spector
1987 Journal of the ACM  
A structural property of the replicated directory that permits the construction of an efficient algorithm for deletions is proven.  ...  Efficient algorithms are presented for all of the standard directory operations.  ...  Acknowledgments James Driscoll suggested improvements to our inidal dynamic partitioning algorithm that resulted in the data structure described in tiiis paper.  ... 
doi:10.1145/31846.31847 fatcat:fphgp5syorfxnjp7jg7xuqxteu

A replicated file system for Grid computing

Jiaying Zhang, Peter Honeyman
2008 Concurrency and Computation  
To meet the rigorous demands of large-scale data sharing in global collaborations, we present a replication scheme for NFSv4 that supports mutable replication without sacrificing strong consistency guarantees  ...  With the introduction of a hierarchical replication control protocol, the overhead of replication is negligible even when applications mostly write and replication servers are widely distributed.  ...  Scanning the directory tree during the check is too expensive, so we do some bookkeeping when electing a primary server: each replication server maintains an ancestry table for files and directories whose  ... 
doi:10.1002/cpe.1286 fatcat:shwbuglgevfmteh6cpdf4pgbai

Perspectives on optimistically replicated, peer-to-peer filing

T. W. Page, R. G. Guy, J. S. Heidemann, D. H. Ratner, P. L. Reiher, A. Goel, G. H. Kuenning, G. J. Popek
1998 Software, Practice & Experience  
of directory replicas.  ...  The paper concludes with a number of lessons learned from the experience of designing, building, measuring, and living with an optimistcally replicated le system.  ...  Insert delete ambiguity Consider two copies of a directory: the rst has an entry for le F and the second does not.  ... 
doi:10.1002/(sici)1097-024x(199802)28:2<155::aid-spe155>3.0.co;2-5 fatcat:s2uywgl3lfgxbit6arolehttmq

Query routing in the TerraDir distributed directory

Bujor Silaghi, Samrat Bhattacharjee, Peter J. Keleher, Victor Firoiu, Zhi-Li Zhang
2002 Scalability and Traffic Control in IP Networks II  
TerraDir is a wide-area distributed directory designed for hierarchical namespaces, and provides a lookup service for mapping keys to objects.  ...  The TerraDir load balancing scheme also incorporates a node replication algorithm that provides configurable failure resilience with provably low overheads. . † Napster, Gnutella, and Morpheus are examples  ...  This paper is organized as follows: in Section 2, we present an overview of the TerraDir directory protocols and discuss our caching and replication algorithms.  ... 
doi:10.1117/12.475281 fatcat:errr5nhv3jghzbg35z67bzypx4

File system on CRDT [article]

Mehdi Ahmed-Nacer, Stéphane Martin (INRIA Lorraine - LORIA), Pascal Urso
2012 arXiv   pre-print
This structure is optimistically replicated, each user work on his local replica, and updates are sent to other replica. The different replicas eventually observe same view of file systems.  ...  In figure17 a tree observed by user is : root/directory/movie.java and root/directory/movie.avi. When user makes modification in the file movie.java, an algorithm used is automatically Logoot.  ...  ). • pre(update(p, t, p , u), S) ≡ exists(p, S) In addition, the directories must not have an extension and text type are not permitted as an extension for binary files.  ... 
arXiv:1207.5990v1 fatcat:bvomigrhcvckhpcmzjtmlemk6e

Pangaea

Yasushi Saito, Christos Karamanolis
2002 Proceedings of the 10th workshop on ACM SIGOPS European workshop: beyond the PC - EW10  
Our evaluation shows that this algorithm consumes only 5% more network bandwidth than an idealized optimal algorithm.  ...  We present simple randomized algorithms for maintaining these graphs in Section 2.  ... 
doi:10.1145/1133373.1133421 dblp:conf/sigopsE/SaitoK02 fatcat:5hc7xetf2rdcxjo3yjjnzdwqdm

Reducing the Availability Management Overheads of Federated Content Sharing Systems

Christopher Peery, Thu Nguyen, Francisco Cuenca-acuna
2006 Symposium on Reliable Distributed Systems. Proceedings  
Our replication algorithm centers around the intuition that devices should selfishly use their local storage to ensure offline and ownership availability for their individual owners.  ...  We propose a novel unified availability model and a decentralized replication algorithm to approximate this ideal.  ...  In this paper, as already described, our algorithm maintains an LRU working set for simplicity.  ... 
doi:10.1109/srds.2006.39 dblp:conf/srds/PeeryNC06 fatcat:uxw57uz745h45p3zxcmddhncii
« Previous Showing results 1 — 15 out of 18,037 results