Cross-Layer Data-Integrity Qualification of GPU-Direct Storage Paths Using NVMe-oF and DPU Offload
Sciences du Nord Nature Science and Technology · 31.12.2025 · 2 (02) · 105-116
DOI: 10.71238/snnst.v2i02.201 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sciences du Nord Nature Science and Technology, online erschienen am 31.12.2025. Verfasst von Gagan Vyas. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
GPUDirect Storage over NVMe over Fabrics (NVMe-oF), more often now combined with data processing unit (DPU) offload, has reduced the latency from flash to accelerator memory but eliminated the host-side copy at which payloads were conventionally sifted, and silent data corruption (SDC) is a documented problem at fleet scale. It was desired to find a cross-layer data-integrity qualification scheme for these paths. We performed a systematic review of 17 publications (3 journal articles, 7 conference or book-series papers and 7 preprints). The evidence was structured with nine equations that describe residual corruption probability, digest coverage, verification overhead, offload overlap and test-pass sizing and was categorised by function (path layer) and offloading. There were five path layers related to fault classes, detection mechanisms, qualification tests. NVMe-oF was reported to increase the access time by 11.7 µs, while iSCSI decreased key-value throughput by 40%. Offload gains of 15% in training time and 2.8 times in throughput were achieved without reporting any overhead for verification. In an illustrative model, transport-only digests left about 977 expected undetected events per exabyte, while end-to-end coverage left 8.0 × 10−7 expected undetected events per exabyte. The level of integrity is a path-level property and needs to be accompanied by overheads for integrity verification along with offload efficiency. The review provides a multi-layer qualification matrix and a quantitative model that are still valid in case of migrating storage functions to the DPU.
Zitieren
APA
Vyas, G. (2025). Cross-Layer Data-Integrity Qualification of GPU-Direct Storage Paths Using NVMe-oF and DPU Offload. Sciences du Nord Nature Science and Technology, 2(02), 105-116. https://doi.org/10.71238/snnst.v2i02.201
Vancouver
Vyas G. Cross-Layer Data-Integrity Qualification of GPU-Direct Storage Paths Using NVMe-oF and DPU Offload. Sciences du Nord Nature Science and Technology. 2025;2(02):105-116. doi:10.71238/snnst.v2i02.201
BibTeX
@article{Vyas2025,
author = {Vyas, Gagan},
title = {Cross-Layer Data-Integrity Qualification of GPU-Direct Storage Paths Using NVMe-oF and DPU Offload},
journal = {Sciences du Nord Nature Science and Technology},
year = {2025},
volume = {2},
number = {02},
pages = {105--116},
doi = {10.71238/snnst.v2i02.201}
}
EUVIMED