EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC 4.0

Making In-Memory Learned Indexes Efficient on Disk

Jiaoyi Zhang, Kai Su, Huanchen Zhang

Proceedings of the ACM on Management of Data · 29.05.2024 · 2 (3) · 1-26

DOI: 10.1145/3654954 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the ACM on Management of Data, online erschienen am 30.05.2024. Verfasst von Jiaoyi Zhang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 21-mal zitiert (Crossref) und nennt 37 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Learned indexes have been demonstrated to outperform traditional ones in memory-resident scenarios. However, recent studies show that they fail to outperform B+tree when extended to disks directly. In this paper, we argue that it is feasible to create efficient disk-based learned indexes by applying a set of general transformations and optimizations to existing in-memory ones. Through theoretical analysis and controlled experiments, we propose six transformation guidelines applicable to various state-of-the-art learned index structures to fully leverage the characteristics of disk storage. Our evaluation shows that the indexes developed by applying our guidelines achieve a Pareto improvement in both throughput and space efficiency compared to the traditional B+tree and previous implementations of disk-based learned indexes.

Zitieren

APA

Zhang, J., Su, K., & Zhang, H. (2024). Making In-Memory Learned Indexes Efficient on Disk. Proceedings of the ACM on Management of Data, 2(3), 1-26. https://doi.org/10.1145/3654954

Vancouver

Zhang J, Su K, Zhang H. Making In-Memory Learned Indexes Efficient on Disk. Proceedings of the ACM on Management of Data. 2024;2(3):1-26. doi:10.1145/3654954

BibTeX
@article{Zhang2024,
  author = {Zhang, Jiaoyi and Su, Kai and Zhang, Huanchen},
  title = {Making In-Memory Learned Indexes Efficient on Disk},
  journal = {Proceedings of the ACM on Management of Data},
  year = {2024},
  volume = {2},
  number = {3},
  pages = {1--26},
  doi = {10.1145/3654954}
}
Kostenlos starten →