Overview and Evaluation of the Server Redundancy and Session Failover Mechanisms

The number of availability-critical Internet applications is steadily increasing. To support the development and op-eration of such applications, the IETF has recently defined a new standard for a common server redundancy and session failover framework: Reliable Server Pooling (RSerPool). The basic ideas of the RSerPool framework are not entirely new, but their combination into a single, resource-efficient and unified architecture is. Service availability achieved by the redundancy of servers directly leads to the issues of load distribution and load balancing, which are both important for the performance of RSerPool systems. Therefore, it is crucial to evaluate the performance of such systems with respect to the load balancing strategy required by the ser-vice application. In this article – which is an extended version of our pa-per [1] – we first present an overview of the RSerPool ar-chitecture with a focus on the component failure detection and handling mechanisms. We will also shortly introduce the underlying SCTP protocol and its link redundancy fea-tures. After that, we will present a quantitative, application-independent performance analysis of the failure detection and session failover mechanisms provided by RSerPool, with respect to important adaptive and non-adaptive load balancing strategies