EDFI: A Dependable Fault Injection Tool for Dependability Benchmarking Experiments

Research output: Chapter in Book / Report / Conference proceedingConference contributionAcademicpeer-review

Abstract

Fault injection is a pivotal technique in dependability benchmarking. Unfortunately, existing general-purpose fault injection tools either inject faults in predetermined memory locations or resort to random injection, approaches that generally result in poor fault coverage and controllability guarantees. This makes it difficult to reproduce or compare experiments across different systems or workloads. This paper presents EDFI, a new tool for dependable general-purpose fault injection experiments. EDFI combines static and dynamic program instrumentation to perform execution-driven fault injection, a technique which allows realistic software faults to be injected in a controlled way as the target system executes. Our instrumentation strategy guarantees a predetermined fault load distribution during the entirety of the experiment, independently of the particular system or workload considered. Our evaluation confirms that EDFI significantly improves the precision and controllability of prior tools, at the cost of only modest memory and performance overhead during fault-free execution.
Original languageEnglish
Title of host publicationProceedings of the Pacific Rim International Symposium on Dependable Computing
PublisherIEEE CS
Pages31-40
ISBN (Electronic)978-0-7695-5130-2
DOIs
Publication statusPublished - 2013

Fingerprint

Dive into the research topics of 'EDFI: A Dependable Fault Injection Tool for Dependability Benchmarking Experiments'. Together they form a unique fingerprint.

Cite this