Protocol Conversion

The difficulty of interconnecting networks or network components when they obey different architectures is an important inhibitor to computer communication growth and flexibility. This paper reviews the state of the protocol conversion art from the architectural point of view. The aim is to state the problem succinctly, propose consistent definitions, review current ad hoc solutions, and speculate about more effective and general methodologies. To do this, we first analyze what happens on an access path between two end users at the discontinuity point where the path passes from a portion of the network obeying one architecture into a portion obeying another. This discontinuity can be designed to occur at a choice of nodes along the access path and at a choice of protocol layer level at each such node. The process of conversion to complete the path at one of these points can range in complexity from the trivial to the impossible. The procedure available today starts by analyzing the set of "atomic protocol functions" that support the services normally provided at the conversion point by the two architectures in terms of their interface, peer and control protocols (both transient and steady state), and then identifying a usable common subset of the two sets. Known solutions then include defining useful partial resolution of protocol mismatches, complementation of one or both protocols with missing services, and the use of Open System Interconnection as an intermediary in the conversion process.