Metraipolis › archive › dc_e3d1ced34f80

TriFleetRCA: On-Premise LLM Root Cause Analysis for Kubernetes — arXiv:2609.23766

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.23766
License (as archived)
CC0-1.0
Archived
2026-10-09T06:53:11.689Z
SHA-256 of the archived text
a74f178ab11e5ea4ff40a679c8994dbd2e09266ba91dfcd189d45d9ae1d88d68
Stable URL of this page
https://metraipolis.com/documento/dc_e3d1ced34f80

How to cite

TriFleetRCA: On-Premise LLM Root Cause Analysis for Kubernetes — arXiv:2609.23766 — arXiv (en), https://arxiv.org/abs/2609.23766 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e3d1ced34f80 (Metraipolis archive dc_e3d1ced34f80, sha256 a74f178ab11e5ea4ff40a679c8994dbd2e09266ba91dfcd189d45d9ae1d88d68)
BibTeX
@misc{dce3d1ced34f80,
  title = {TriFleetRCA: On-Premise LLM Root Cause Analysis for Kubernetes — arXiv:2609.23766},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.23766},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e3d1ced34f80; sha256 a74f178ab11e5ea4ff40a679c8994dbd2e09266ba91dfcd189d45d9ae1d88d68},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.23766. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Root cause analysis at a remote site is slow: evidence is scattered across pod logs, Kubernetes events and cluster-level objects, and many operators cannot send production logs to a hosted model at all. On-premise inference removes the second constraint but raises a question live-cluster benchmarks have not addressed: when one workstation GPU fixes both the model and the context budget, how should evidence be retrieved, and what happens when the runbooks the model consults have been tampered with? We present TriFleetRCA, a pipeline running entirely on one on-premise GPU that collects evidence at one of three scopes (pod, namespace, cluster), ranks it by template de-duplication then BM25, filters runbooks through an ingest guard, and returns a root cause with the evidence lines supporting it. We evaluate on a live Kubernetes cluster into which we inject four faults, so ground truth is known by construction, across 100 analyses with Qwen2.5-14B-Instruct at temperature 0. The hit rate was 0.85, 0.90 and 0.95 at pod, namespace and cluster scope; intervals overlap, but the whole scope effect comes from the one fault whose cause is a cluster-level object, and cluster scope costs 55% more tokens. De-duplication before ranking raised the hit rate from 0.75 to 0.90 at equal token cost. A poisoned runbook telling the model to delete the namespace was rejected by the guard every run; with the guard disabled the model declined to follow it in all 20 analyses, making the guard defence in depth rather than the sole barrier. Separating citation quality from accuracy proved informative: one fault was diagnosed correctly and cited incorrectly every trial, a failure mode accuracy conceals. Median latency was 1.6 s at 2,200 prompt tokens. We release the pipeline, the fault injector and all records.

Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-22 in cs.DC).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI); Distributed, Parallel, and Cluster Computing (cs.DC); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.23766 — 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 2026-10-09T06:50:13.563Z dalla pagina https://arxiv.org/catchup/cs.DC/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).