Metraipolis › archive › dc_fe10efaf4234
Beyond Fixed Fault Models: Comparing LLM-Based and Rule-Based Fault Injection in OpenStack — arXiv:2609.08681
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.08681
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T14:09:12.713Z
- SHA-256 of the archived text
471bf347464ac4ff2119363f4d2573492773636ebfdcbb7ee1135f2510c47f47- Stable URL of this page
https://metraipolis.com/documento/dc_fe10efaf4234
How to cite
Beyond Fixed Fault Models: Comparing LLM-Based and Rule-Based Fault Injection in OpenStack — arXiv:2609.08681 — arXiv (en), https://arxiv.org/abs/2609.08681 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fe10efaf4234 (Metraipolis archive dc_fe10efaf4234, sha256 471bf347464ac4ff2119363f4d2573492773636ebfdcbb7ee1135f2510c47f47)
BibTeX
@misc{dcfe10efaf4234,
title = {Beyond Fixed Fault Models: Comparing LLM-Based and Rule-Based Fault Injection in OpenStack — arXiv:2609.08681},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.08681},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fe10efaf4234; sha256 471bf347464ac4ff2119363f4d2573492773636ebfdcbb7ee1135f2510c47f47},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.08681. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Software Fault Injection (SFI) supports testing of cloud systems by introducing software defects and observing their manifestation. Rule-based injectors such as ProFIPy provide controlled and reproducible source-level mutations but require fault patterns to be encoded manually. Large Language Models (LLMs) offer a data-driven alternative by generating context-dependent software faults. We compare two code LLMs, Qwen2.5-Coder and DeepSeek-Coder, with ProFIPy in OpenStack's Nova and Cinder services. On shared injection targets, activation and observable-failure rates are comparable, but operational profiles differ: LLM-generated faults produce more Catastrophic outcomes on Nova, whereas ProFIPy produces more Silent and Multi-component effects. The sampled LLM outputs also differ in how they manifest failure, while showing greater agreement in their propagation scope. These findings show that LLM-based fault injection extends the behavioral coverage of fixed fault models without establishing general superiority, and that practical adoption still requires controlled generation, runtime validation, system-level oracles, and reproducible experimental provenance. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-09 in cs.SE). Categorie arXiv: Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2609.08681 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-16T13:58:36.418Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).