An ef cient topology-adaptive membership protocol for large-scale network services

A highly available large-scale service cluster often requires the system to discover new nodes and identify failed nodes quickly in order to handle a high volume of traffic. Determining node membership efficiently in such an environment is critical to location-transparent service invocation, load balancing and failure shielding. In this paper, we present a topology-aware hierarchical membership service which divides the entire cluster into membership groups based on the network topology among nodes so that the liveness of a node within each group is published to others in a highly efficient manner. Our design also supports the deployment of service clusters in multiple data centers through membership proxies which update membership information incrementally so that membership communication across data centers is minimized as much as possible. We compare our approach with other two alternatives: an all-to-all multicasting approach and a gossip based approach. Our evaluation shows that the proposed topology-aware approach is scalable and effective in terms of high membership accuracy, short view convergence time, and low communication cost.