90 likes | 107 Views
This paper explores a novel approach to addressing multi-dimensional queries in P2P systems, with applications in photo-sharing and multiplayer online games. The system's components include a partitioning strategy that distributes data across nodes using space-filling curves with range partitioning. The routing strategy ensures efficient query transmission to relevant nodes by converting multi-dimensional queries into a series of 1-dimensional range queries. Key desiderata such as locality, load balance, minimal metadata, low state, and efficient query routing are achieved through innovative techniques like skip graphs. This paper provides insights into building scalable and optimized P2P systems for diverse applications.
E N D
Applications • Photo-sharing (photographs tagged with metadata) • Multi-player online games (locate objects and other users)
System’s Components • Partitioning Strategy (distribute data across nodes) • Routing Strategy (transmit a query to the relevant nodes)
Partitioning Strategy • Data are mapped into a single dimension e.g. (0100,0101) -> 01000101 • Single-dimensional data are range-partitioned across a dynamic set of nodes
Routing Strategy • Multi-dimensional range query is converted to a set of 1-d range queries • Route each of 1-d range queries (Skip graph: A Chord-like connection between the nodes, which promises O(logn) messages)
Desiderata • Locality: Nearby data points in the multi-dimensional space are also adjacent in the single dimension • Load Balance: • Management of neighboring ranges • Node with empty partition splits the range of heavily loaded node
Desiderata • Minimal metadata : Each node knows only partition boundaries of itself and its neighbors • Low state : O(logn) links per node • Routing load balance : Achieved due to the symmetric nature of skip graphs • Query routing : O(logn) hops for each 1-d