A Memory Efficient Result Cache Scheme for P2P DHT Based on Bloom Filters

• ARIYOSHI Takahiro

  Department of Information Engineering, Graduate School of Engineering, Hiroshima University

• FUJITA Satoshi

  Department of Information Engineering, Graduate School of Engineering, Hiroshima University

Abstract

In this paper, we study the problem of efficient processing of conjunctive queries in Peer-to-Peer systems based on Distributed Hash Tables (P2P DHT, for short). The basic idea of our approach is to cache the search result for the queries submitted in the past, and to use them to improve the performance of succeeding query processing. More concretely, we propose to adopt Bloom filters as a concrete implementation of such a result cache rather than a list of items used in many conventional schemes. By taking such an approach, the cache size for each conjunctive query becomes as small as the size of each file index. The performance of the proposed scheme is evaluated by simulation. The result of simulation indicates that the proposed scheme is particularly effective when the size of available memory in each peer is bounded by a small value, and when the number of peers is 100, it reduces the amount of data transmissions of previous schemes by 75%.

Journal

• IEICE Transactions on Information and Systems

  IEICE Transactions on Information and Systems E94-D (8), 1602-1609, 2011

  The Institute of Electronics, Information and Communication Engineers

Keywords

• peer-to-peer
• Distributed Hash Table
• conjunctive query
• bloom filter

Details

• CRID: 1390001204379138816
• NII Article ID: 10030192510
• NII Book ID: AA10826272
• DOI: 10.1587/transinf.e94.d.1602
• ISSN: 17451361
• ISSN: 09168532
• Web Site: http://www.jstage.jst.go.jp/article/transinf/E94.D/8/E94.D_8_1602/_pdf
• Text Lang: en
• Data Source:
  • JaLC
  • Crossref
  • CiNii Articles
  • KAKEN
• Abstract License Flag: Disallowed