The Armada model describes how a distributed database system evolves, using multiple nodes that together form the database. In such system, posing a query involves continuously locating the right node until sucient data to answer the query has been found. Locating a node involves making a connection to such node. Since making a connection is expensive in time, avoiding to do so where possible, pays oin the total query execution time. In this short paper, we give an extended summary of our work on cutting down the number of made connections per query in an Armada system
Workshop on Dependable Distributed Data Management
Database Architectures

Groffen, F., Kersten, M., & Manegold, S. (2009). Optimising client accesses within Armada. In Proceedings of Third Workshop on Dependable Distributed Data Management (WDDDM 2009).