Scalable Persistent Memory File System with Kernel-Userspace Collaboration

Authors: 

Youmin Chen, Youyou Lu, and Bohong Zhu, Tsinghua University; Andrea C. Arpaci-Dusseau and Remzi H. Arpaci-Dusseau, University of Wisconsin–Madison; Jiwu Shu, Tsinghua University

Abstract: 

We introduce Kuco, a novel direct-access file system architecture whose main goal is scalability. Kuco utilizes three key techniques – collaborative indexing, two-level locking, and versioned reads – to offload time-consuming tasks, such as pathname resolution and concurrency control, from the kernel to userspace, thus avoiding kernel processing bottlenecks. Upon Kuco, we present the design and implementation of KucoFS, and then experimentally show that KucoFS has excellent performance in a wide range of experiments; importantly, KucoFS scales better than existing file systems by up to an order of magnitude for metadata operations, and fully exploits device bandwidth for data operations.

FAST '21 Open Access Sponsored by NetApp

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@inproceedings {264812,
author = {Youmin Chen and Youyou Lu and Bohong Zhu and Andrea C. Arpaci-Dusseau and Remzi H. Arpaci-Dusseau and Jiwu Shu},
title = {Scalable Persistent Memory File System with Kernel-Userspace Collaboration},
booktitle = {19th {USENIX} Conference on File and Storage Technologies ({FAST} 21)},
year = {2021},
isbn = {978-1-939133-20-5},
pages = {81--95},
url = {https://www.usenix.org/conference/fast21/presentation/chen-youmin},
publisher = {{USENIX} Association},
month = feb,
}

Presentation Video