Fault injection techniques and tools

Abstract

Fault injectionis important to evaluating the dependability of computer systems.Researchers and engineers have created many novel methods to inject faults, which can be implemented in both hardware and software.ependability evaluation involves the study of failures and errors. The destructive nature of a crash and long error latency make it difficult to identify the causes of failures in the operational environment.It is particularly hard to recreate a failure scenario for a large, complex system.To identify and understand potential failures, we use an experiment-based approach for studying the dependability of a system. Such an approach is applied not only during the conception and design phases, but also during the prototype and operational phases, t; To take an experiment-based approach, we must first understand a system's architecture, structure, and behavior. Specifically, we need to know its tolerance for faults and failures, including its built-in detection and recovery mechanisms, 3 and we need specific instruments and tools to inject faults, create failures or errors, and monitor their effects. DIFFERENT PHASES, DIFFERENT TECHNIQUESEngineers most often use low-cost, simulationbased fault injection to evaluate the dependability of a system that is in the conceptual and design phases. At this point, the system under study is only a series of high-level abstractions; implementation details have yet to be determined, Thus the system is simulated on the basis of simplified assumptions. Simulation-based fault injection, which assumes that errors or failures occur according to-predetermined dismbutio_ is mefd, for evaluating theeffe¢-! tiveaemof fault-toleran__ and a_ whid/hre:difflcult to_supp_ measurements. Testing a prototype, on the other hand, allows us to evaluate the system without any assumptions about system design, which yields more accurate results. In prototype-based fault iniection, we inject faults into the system to • identify dependability bottlenecks,• study system behavior in the presence of faults,• determine the coverage of error detection and recovery mechanisms, and • evaluate the effectiveness of fault tolerance mechanisms (such as reconfiguration schemes) and performance loss.To do prototype-based fault injection, faults are injected either at the hardware Level (logical or electrical faults) or at the software level (code or data corruption) and the effects are monitored. The system used for evaluation can be either a prototype or a fully operational system. Injecting faults into an operational system can provide information about the failure process. However, fault injection is suitable for studying emulated faults only. It also fails to provide dependability measures such as mean time between failures and availability.

ARROW - A Generic Hardware Fault Injection Tool for NoCs

“…To reduce costs in manufactoring, verfication and test, chips may be built with a kind of fault tolerance so that they may not suffer under the requirement of being 100% perfect [23]. The recreation of failure scenarios becomes a too hard task to be managed and hence, to be able to validate fault tolerance and to understand the potential failures of a system, a kind of an experimental approach, called fault injection is needed [20]. By mischance, many tools are written for a particular design and therefore not reusable.…”

“…In this context, the system is described as a series of high level abstractions with no low level implementation details to be determined [20]. It is very useful for evaluating the effectiveness of fault tolerance during the early design phase, allowing to save costs in the design process, avoiding redesigning in case of faulty beahvior and finally resulting in shorter time to market.…”

“…This method is only proper, if the target system is an application or an operating system. An overview over software fault injection can be found in [20]. Common used tools are for example "Ferrari" or "DOCTOR".…”

Classification Framework for Analysis and Modeling of Physically Induced Reliability Violations

“…In Hsueh et al [1997], we find a presentation of fault injection techniques. The basic distinction is between fault injection performed in the HW (either with or without a physical contact) and in the SW (either at compilation time or at runtime).…”

FIEEV: A co-simulation framework for Fault Injection in electrical vehicles

“…For example, we believe it is crucial to develop a new simulation tool specifically targeted for fault modeling that will promote ease of specifications of complex fault behaviors, such as their form, time behavior and fault hierarchies, allowing the engineer to create simple but realistic models for precise safety analysis and vehicle stability studies. As referred by [6], engineers most often use fault injection tools like this to evaluate dependability of systems in the conceptual and design phases. It is also stated that the prototype-based fault injection technique is performed to study systems behavior in presence of faults and also to evaluate the effectiveness of fault tolerant mechanisms.…”