Complex Queries in P2P Networks with Resource-Constrained Devices

Structured Peer-to-Peer (P2P) systems are increasingly important for scalable data dissemination and search. At the same time, the importance of mobile devices like smartphones, PDAs, and netbooks for accessing and storing data is rapidly increasing. Current distributed approaches for resolving complex search queries, like multi-attribute and range queries, typically require multiple messages to resolve a single search request. This generates significant messaging overhead and increases the response latency. To reduce the messaging overhead and the search latency, some approaches like the Multi-Attribute Addressable Network (MAAN) use static replication. However, this results in high main memory requirements and large data transfers each time a device joins the P2P network. Those drawbacks can be tolerated for P2P networks that mainly consist of fixed, powerful nodes like PCs but are intolerable for resource-constrained nodes with high churn, like mobile devices. As mobile devices will play a significant role in accessing and distributing data in the future, we present an improved search mechanism for distributed resolution of complex queries on resourceconstrained devices. Compared to MAAN, our approach significantly reduces the memory footprint and bandwidth requirements (up to a factor of three – five, depending on the load model and the type of query in our sample scenario). At the same time, the good latency properties and the low messaging overhead of MAAN are retained on average. This is achieved via a dynamic replication scheme which introduces an adjustable trade-off between memory footprint and search latency. Thereby, our approach makes efficient, distributed resolution of complex queries on resource-constrained devices feasible, allowing such devices to live up to their important role in the future.

[1]  Florian Schintke,et al.  Range queries on structured overlay networks , 2008, Comput. Commun..

[2]  Benjamin Van Roy,et al.  Consensus Propagation , 2005, IEEE Transactions on Information Theory.

[3]  Margo I. Seltzer,et al.  Distributed, secure load balancing with skew, heterogeneity and churn , 2005, Proceedings IEEE 24th Annual Joint Conference of the IEEE Computer and Communications Societies..

[4]  Artur Andrzejak,et al.  Scalable, efficient range queries for grid information services , 2002, Proceedings. Second International Conference on Peer-to-Peer Computing,.

[5]  Stephen P. Boyd,et al.  Fast linear iterations for distributed averaging , 2003, 42nd IEEE International Conference on Decision and Control (IEEE Cat. No.03CH37475).

[6]  Thorsten Biermann,et al.  An Adaptive Resource/Performance Trade-Off for Resolving Complex Queries in P2P Networks , 2009, 2009 IEEE International Conference on Communications.

[7]  Tim Moors,et al.  Survey of Research towards Robust Peer-to-Peer Networks: Search Methods , 2007, RFC.

[8]  Aruna Seneviratne,et al.  Supporting mobile devices in Gnutella file sharing network with mobile agents , 2003, Proceedings of the Eighth IEEE Symposium on Computers and Communications. ISCC 2003.

[9]  Robert Morris,et al.  Chord: A scalable peer-to-peer lookup service for internet applications , 2001, SIGCOMM 2001.

[10]  C. Dannewitz Augmented Internet: An Information-Centric Approach for Real-World / Internet Integration , 2009, 2009 IEEE International Conference on Communications Workshops.

[11]  Srinivasan Seshan,et al.  Mercury: supporting scalable multi-attribute range queries , 2004, SIGCOMM 2004.

[12]  Qi Zhang,et al.  An efficient algorithm for approximate biased quantile computation in data streams , 2007, CIKM '07.

[13]  Manish Parashar,et al.  Enabling flexible queries with guarantees in P2P systems , 2004, IEEE Internet Computing.

[14]  David R. Karger,et al.  Consistent hashing and random trees: distributed caching protocols for relieving hot spots on the World Wide Web , 1997, STOC '97.

[15]  Min Cai,et al.  MAAN: A Multi-Attribute Addressable Network for Grid Information Services , 2003, Journal of Grid Computing.