Efficient Distributed CQ Processing using Peers

Wee Siong Ng, Beng Chin Ooi, Yanfeng Shu, Kian-Lee Tan, Wee Hyong Tok

Abstract: In this paper, we propose a framework called CQ-Buddy, for supporting distributed continuous query (CQ) processing system based on Peer-to-Peer (P2P) technology. Working on the basis of peer heterogeneity, peers in a CQ-Buddy network "help" one another by sharing query workload and providing data. Our main contributions are as follows: first, CQ-Buddy introduces a novel class of queries, called pervasive continuous queries , for disconnected operations which are common in the peer-to-peer environment; second, the framework presents two strategies, SELF-HELP , and BUDDY-HELP , that allow for the grouping and sharing of multiple continuous queries amongst peers; third, by keeping peers that are processing the continuous queries in close proximity, the network bandwidth can be more effectively utilized. We conduct an extensive performance study to evaluate the proposed strategies, and our results show the effectiveness of the proposed schemes.