Abstract: A method of and apparatus for distributing data for a database between a plurality of processors in a distributed processor system involves running a database management system on a first plurality of processors in conjunction with a plurality of protocols that generate or amend data for the database. Data is distributed from servers to clients registered in a server-client relationship. Server-client relationships may also be registered between a second, and a third plurality of processors that do not run protocols generating or amending data for the database. Fault tolerant redundancy is provided by clients registering with two or more servers, one as a primary and another as a secondary, and activating the secondary if the primary fails. The method is particularly applicable to scalable data packet routers having a plurality of processors operating on different line and control cards.