A proof methodology for verification of real-time and fault-tolerance properties of distributed programs

From the early days of programming, the dependability of software has been a concern. The development of distributed systems that must respond in real-time and continue to function correctly in spite of hardware failure have increased the concern while making the task of ensuring dependability more complex. This dissertation presents a technique for improving confidence in software designed to execute on a distributed system of fail-stop processors. The methodology presented is based on a temporal logic augmented with time intervals and probability distributions. A temporal logic augmented with time intervals, Bounded Time Temporal Logic (BTTL), supports the specification and verification of real-time properties such as, "The program will poll the sensor every t to T time units." Analogously, a temporal logic augmented with probability distributions, Probabilistic Bounded Time Temporal Logic (PBTTL), supports reasoning about fault-tolerant properties such as, "The program will complete with probability less than or equal to p", and a combination of these properties such as, "The program will complete within t and T time units with probability less than or equal to p." The syntax and semantics of the two logics, BTTL and PBTTL, are carefully developed. This includes development of a program state model, state transition model, message passing system model and failure system model. An axiomatic program model is then presented and used for the development of a set of inference rules. The inference rules are designed to simplify use of the logic for reasoning about typical programming language constructs and commonly occurring programming scenarios. In addition to offering a systematic approach for verifying typical behaviors, the inference rules are intended to support the derivation of formulas expressing timing and probabilistic relationships between the execution times and probabilities of individual statements, groups of statements, message passing and failure recovery. Use of the methodology is demonstrated in examples of varying complexity, including five real-time examples and four combined real-time and fault-tolerant examples