ER-TCP: An efficient fault-tolerance scheme for TCP connections

This paper proposes a novel scheme, called ER-TCP, which transparently masks the failures on the server nodes in a cluster from clients at TCP connection level. Connections at the server side are actively and fully replicated to remain consistency. A log mechanism is designed to cooperate with the replication to achieve small sacrifice on the performance of communication and makes the scheme scale beyond a few nodes, even when they have different processing capacities. The scheme is justified by experiments conducted on prototype implementation.