Abstract
A large number of peer processes are cooperating by exchanging messages in autonomic, Peer-to-Peer (P2P) systems. In this paper, we discuss a Hierarchical Group (HG) protocol aimed at reducing communication and computation overheads for a large number of processes. A HG is composed of disjointed subgroups. Each subgroup has gateway processes which communicate with other subgroups. Even if messages are locally causally ordered in a subgroup, the messages may not be globally causally ordered in a group. We discuss how to globally causally order messages by using local synchronisation mechanisms of subgroups. In addition, we present an evaluation of the protocol.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call