Improving Performance of Declarative Query Execution in DHT-Based Systems

Peer-to-peer systems based on Distributed Hash Tables face tradeoffs between the performance (latency or availability) and their desired functionality. In fact, lookup latency is affected by the mismatch problem between the overlay hop and the underlying topology. So, applications built on top of such systems can be impacted. A core problem in peer-to-peer systems is the distribution of items to be stored or computations to be carried out by peers in the system. Many works have been done concerning storage and key distribution but little work has been done regarding the distribution of operations carried out by peers in the system. This paper presents a query execution load balancing strategy that allows improving performance of declarative query execution in P2P DHT-based systems. A performance evaluation, using Grid5000 platform, is provided to verify the improvement achieved by the strategies presented.