A Dynamic Hashing Approach to Supporting Load Balance in P2P Systems

Abstract

In a structured P2P system, peers maintain information about what resources neighbor peers offer. Chord is one of well-known structured P2P systems to efficiently support resource finding based on the hashing approach. However, in Chord, most of data keys may be assigned to the same peer, since it uses the static hashing scheme, resulting in the case that the load of Chord is unbalanced. Therefore, we propose a strategy which uses the dynamic hashing scheme to locate the data key based on the Chord architecture, and to maintain the load balance. From our simulation results, we show that the load of the P2P system based on our strategy is much more balanced than that based on the original strategy used in Chord.

HistoChain: Improving Consortium Blockchain Scalability using Historical Blockchains

“…Their approach is based on the state of the server clusters and periodically sends collected feedback to the load balancer to bring the internal load performance of the system to a more balanced state. In [21], the authors introduced a strategy to use a dynamic hashing scheme to locate data keys based on a structured P2P architecture and maintain the load balance among the peers. They showed that the load balancing of P2P systems can be significantly improved using their proposed method.…”