F. Grandoni

Threshold-based mechanisms to discriminate transient from intermittent faults

This paper presents a class of count-and-threshold mechanisms, collectively named /spl alpha/-count, which are able to discriminate between transient faults and intermittent faults in computing systems. For many years, commercial systems have been using transient fault discrimination via threshold-based techniques. We aim to contribute to the utility of count-and-threshold schemes, by exploring their effects on the system. We adopt a mathematically defined structure, which is simple enough to analyze by standard tools. /spl alpha/-count is equipped with internal parameters that can be tuned to suit environmental variables (such as transient fault rate, intermittent fault occurrence patterns). We carried out an extensive behavior analysis for two versions of the count-and-threshold scheme, assuming, first, exponentially distributed fault occurrencies and, then, more realistic fault patterns.

Discriminating fault rate and persistency to improve fault treatment

In this paper the consolidate identification of faults, distinguished as transient or permanent/intermittent, is approached. Transient faults discrimination has long been performed in commercial systems: threshold-based techniques have been practice for several years for this purpose. The present work aims to contribute to the usefulness of the count-and-threshold scheme, through the analysis of its behaviour and the exploration of its effects on the system. To this goal, the scheme is mechanized as a device named /spl alpha/-count, endowed with a few controllable parameters. /spl alpha/-count tries to balance between two conflicting requirements: to keep in the system those components that have experienced just transient faults; and to remove quickly those affected by permanent or intermittent faults. Analytical models are derived, allowing detailed study of /spl alpha/-counts behaviour; the actual evaluation, in a range of configurations, is performed by standard tools, in terms of the delay in spotting faulty components and the probability of improperly blaming correct ones.

State restoration in a COTS-based N-modular architecture

Mechanisms for restoring the state of a channel in an N-modular redundant architecture are necessary to prevent redundancy attrition due to transient faults and to allow failed channels to be brought back on line after repair. This paper considers software-implemented mechanisms for state restoration (SR) in a generic fault-tolerant architecture in which both the underlying hardware and operating system are commercial off-the-shelf (COTS) components. State restoration involves copying the values of state variables from the active channel(s) across to the joining channel. Concurrent updating of state variables by application tasks is considered. Two state restoration schemes are considered: Running SR and Recursive SR. In the former, each state variable is copied exactly once while concurrent updates are written through to the joining channel. In the latter state variables are copied once and then recopied recursively until no concurrent updates are detected.

Error processing and fault treatment

This chapter briefly recalls how fault tolerance is structured in GUARDS and describes in some detail specific procedures error and fault diagnosis and the state restoration.

The Evolution of Dependable Computing in Italy

This brief history of the evolution of dependable computing in Italy begins at the end of the sixties with the need to produce test sequences and testing tools to verify hardware implemented using discrete components. At the same time, as the relevance of a system approach to the problem of dependability had already been perceived, research work was being started in the academic world in the error detecting and correcting codes fields, and in complex system diagnosis. These studies greatly benefitted from the strong mathematical background of the researchers initially involved. This work was considerably developed during the seventies, following the technological evolution. The difficulties involved in generating tests with high coverage determined the need to embed features for easy testability and diagnosability into system design. The architectural evolution from uniprocessor to multiple processor systems, either in tightly coupled or in loosely coupled configurations, together with the medium term industrial interest in promoting prototyping efforts, particularly in the industrial process control and on-line transaction processing fields, have produced a wide range of studies covering all system aspects (physical configuration, operating systems, programming languages and environments). This interest has steadily grown up until the present days, with increased emphasis being placed on dependability attributes.