FINJ: A Fault Injection Tool for HPC Systems

TL;DR

FINJ is a versatile fault injection tool designed for HPC systems that supports complex experiments, custom workloads, and integration with other tools to simulate diverse fault conditions across many nodes.

Contribution

Introduces FINJ, a high-level fault injection framework enabling complex, customizable, and scalable fault experiments in HPC environments with easy integration capabilities.

Findings

Supports complex fault scenarios in HPC systems

Allows integration with existing fault injection tools

Enables experiments on many interacting nodes

Abstract

We present FINJ, a high-level fault injection tool for High-Performance Computing (HPC) systems, with a focus on the management of complex experiments. FINJ provides support for custom workloads and allows generation of anomalous conditions through the use of fault-triggering executable programs. FINJ can also be integrated seamlessly with most other lower-level fault injection tools, allowing users to create and monitor a variety of highly-complex and diverse fault conditions in HPC systems that would be difficult to recreate in practice. FINJ is suitable for experiments involving many, potentially interacting nodes, making it a very versatile design and evaluation tool.