Principles of distributed database systems (2nd ed.)
Principles of distributed database systems (2nd ed.)
Summary cache: a scalable wide-area web cache sharing protocol
IEEE/ACM Transactions on Networking (TON)
ACM Computing Surveys (CSUR)
Space/time trade-offs in hash coding with allowable errors
Communications of the ACM
Proceedings of the 2001 conference on Applications, technologies, architectures, and protocols for computer communications
Chord: A scalable peer-to-peer lookup service for internet applications
Proceedings of the 2001 conference on Applications, technologies, architectures, and protocols for computer communications
IEEE/ACM Transactions on Networking (TON)
New directions in traffic measurement and accounting
Proceedings of the 2002 conference on Applications, technologies, architectures, and protocols for computer communications
PlanetP: Using Gossiping to Build Content Addressable Peer-to-Peer Information Sharing Communities
HPDC '03 Proceedings of the 12th IEEE International Symposium on High Performance Distributed Computing
Proceedings of the 2003 ACM SIGMOD international conference on Management of data
Self-organization in peer-to-peer systems
EW 10 Proceedings of the 10th workshop on ACM SIGOPS European workshop
An improved construction for counting bloom filters
ESA'06 Proceedings of the 14th conference on Annual European Symposium - Volume 14
A fast indexing algorithm optimization with user behavior pattern
ICPCA/SWS'12 Proceedings of the 2012 international conference on Pervasive Computing and the Networked World
Hi-index | 0.00 |
High performance object locating is the hard undertaking in a distributed system. The quality of this work can be assessed by the response time, space utilization and hit rate which are the essential requirements for large-scale Internet applications. Bloom Filter (BF) is made of a number of hash functions which is the critical part of the object locating algorithm. But how many hash functions in BF are the best remains unsolved. This paper presents a method for estimating those numbers in BF's hash function configuration. Our theoretical analysis for figuring out the optimal hash number is given. That number has been crucial to construct a better BF-based algorithm. In order to verify the correctness of our theoretical result, we establish a simulation environment with 50 million objects which are scattered on one hundred nodes. The experiment for comparing traditional hash function number with our number is given. The experimental result shows that the BF with our optimized parameter can reduce the object locating time by 81- 91 percent. Furthermore, we demonstrate this method can be used in similar content randomly-located distributed systems.