Configuration problems are a thriving application area for declarative knowledge representation that currently experiences a constant increase in size and complexity of knowledge bases. Automated support of the debugging process of such knowledge bases is a necessary prerequisite for effective development of configurators. We show that this task can be achieved by consistency-based diagnosis techniques. Based on the formal definition of consistency-based configuration we develop a framework suitable for diagnosing configuration knowledge bases. During the test phase of configurators, valid and invalid examples are used to test the correctness of the system. In case such examples lead to unintended results, debugging of the knowledge base is initiated. Starting from a clear definition of diagnosis in the configuration domain we develop an algorithm based on conflicts. Our framework is general enough for its adaptation to diagnosing customer requirements to identify unachievable conditions during configuration sessions. A prototype

This paper introduces an automatic debugging framework that relies on model–based reasoning techniques to locate faults in programs. In particular, model–based diagnosis, together with an abstract interpretation based conflict detection mechanism is used to derive diagnoses, which correspond to possible faults in programs. Design information and partial specifications are applied to guide a model revision process, which allows for automatic detection and correction of structural faults.

contained herein are those of the authors and should not be interpreted as necessarily representing the official policies or endorsements, either expressed or implied, of the sponsoring institutions, the U.S. Government or any other entity.

Self-healing, i.e. the capability of a system to autonomously detect failures and recover from them, is a very attractive property that may enable large-scale software systems, aimed at delivering services on a 24/7 fashion, to meet their goals with little or no human intervention. Achieving self-healing requires the elicitation and maintenance of domain knowledge in the form of 〈service failure diagnosis, repair plan 〉 patterns, a task which can be overwhelming. Case-Based Reasoning (CBR) is a lazy learning paradigm that largely reduces this kind of knowledge acquisition bottleneck. Moreover, the application of CBR for failure diagnosis and remediation in software systems appears to be very suitable, as in this domain most errors are re-occurrences of known problems. In this paper, we describe a CBR approach for providing large-scale, distributed software systems with selfhealing capabilities, and demonstrate the practical applicability of our methodology by means of some experimental results on a real world application. 1

Abstract. Even with modern software development methodologies, the actual debugging of source code, i.e., location and identification of errors in the program when errant behavior is encountered during testing, remains a crucial part of software development. To apply model-based diagnosis techniques, which have long been state of the art in hardware diagnosis, for automatic debugging, a model of a given program must be automatically created from the source code. This work describes a model that reflects the execution semantics of the Java language, including exceptions and unstructured control flow, thereby providing unprecedented scope in the application of model-based diagnosis to programs. Besides the structural model building process, a behavioral description of some of the model components is given. Finally, impacts of the modeling decisions on the diagnostic process are considered. 1

Model-based diagnosis applied to computer programs has been studied for several years. Although there are still weaknesses in the used models, especially on dealing with dynamic data structures, the approach has been proven useful for automatic debugging. The weaknesses stem from the fact that heap objects are modeled without considering alias information. Our approach extends the modeling process with a static points-to analysis that reveals the structure and relations between heap objects. This points-to information is then used to improve existing value-based models for Java programs such that the diagnosis engine is able to differentiate between separate data structures. With this extension the set of diagnoses can be reduced for certain types of programs.

This paper summarizes the work done in the course of the Jade project, which deals with automatic debugging of Java programs. Besides a brief introduction to the Jade project, models developed to debug Java programs are evaluated and results are presented. Furthermore, insights gained from the results are discussed and topics for further research are identified.

Software fault localization is one of the (if not the) most expensive, tedious and time consuming activities in program debugging. Therefore, there is a high demand for automatic fault localization techniques that can guide programmers to the locations of faults, with minimal human intervention. This demand has led to the proposal and development of various methods, each of which seeks to make the fault localization process more effective in its own unique and creative way. In this article we provide an overview of several such methods and discuss some of the key issues and concerns that are relevant to fault localization. KEY WORDS: Software fault localization, program debugging, software testing, execution trace, suspicious code

Keywords model-based reasoning, testability, FDIR, fault detection, hardware and software faults, International Space Station, command and data handling, caution and warning, rate monotonic scheduling All of the International Space Station (ISS) systems which require computer control depend upon the hardware and software of the Command and Data Handling System (C&DH) system, currently a network of over 30 386-class computers called Multiplexor/Dimultiplexors (MDMs)[18]. The Caution and Warning System (C&W)[7], a set of software tasks that runs on the MDMs, is responsible for detecting, classifying, and reporting errors in all ISS subsystems including the C&DH. Fault Detection, Isolation and Recovery (FDIR) of these errors is typically handled with a combination of automatic and human effort. We are developing an Advanced Diagnostic System (ADS) to augment the C&W system with decision support tools to aid in root cause analysis as well as resolve differing human and machine C&DH state estimates. These tools which draw from sources in model-based reasoning[16,29], will improve the speed and accuracy of flight controllers by reducing the uncertainty in C&DH state estimation, allowing for a more complete assessment of risk. We have run tests with ISS telemetry and focus on those C&W events which relate to the C&DH system itself. This paper describes our initial results and subsequent plans.

Archives des publications du CNRC (NPArC)