Abstract: A fault-tolerant data processing computer system and method for implementing a distributed two-tier state machine aimed for distributed (replicated) data stores, in which consistency is maintained despite the failure of any number of replicas and communication paths. In the distributed two-tier state machine, one process (device) in a network of processes (devices) is chosen as the leader, and that leader is responsible for executing functions that return state machine commands, and for broadcasting the commands to the other processes. The processes execute the commands in the logical precedence order that corresponds to the order of function executions that return these commands. The system and method ensures that each of the processes issues exactly the same sequence of commands for execution, such that each command in the sequence, except the first one, has a precedent command on which the command logically depends.

Abstract: A fault-tolerant data processing computer system and method for implementing a distributed two-tier state machine aimed for distributed (replicated) data stores, in which consistency is maintained despite the failure of any number of replicas and communication paths. In the distributed two-tier state machine, one process (device) in a network of processes (devices) is chosen as the leader, and that leader is responsible for executing functions that return state machine commands, and for broadcasting the commands to the other processes. The processes execute the commands in the logical precedence order that corresponds to the order of function executions that return these commands. The system and method ensures that each of the processes issues exactly the same sequence of commands for execution, such that each command in the sequence, except the first one, has a precedent command on which the command logically depends.