NyxCache: Flexible and Efficient Multi-tenant Persistent Memory Caching

Kan Wu, Kaiwei Tu, Yuvraj Patel, Rathijit Sen, Kwanghyun Park, Andrea Arpaci-Dusseau, Remzi Arpaci-Dusseau

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract / Description of output

We present NyxCache (Nyx), an access regulation framework for multi-tenant persistent memory (PM) caching that supports light-weight access regulation, per-cache resource usage estimation and inter-cache interference analysis. With these mechanisms and existing admission control and capacity allocation logic, we build important sharing policies such as resource-limiting, QoS-awareness, fair slowdown, and proportional sharing: Nyx resource-limiting can accurately limit PM usage of each cache, providing up to 5x better performance isolation than a bandwidth-limiting method. Nyx QoS can provide QoS guarantees to latency-critical caches while providing higher throughput (up to 6x vs. previous DRAM-based approaches) to best-effort caches that are not interfering. Finally, we show that Nyx is useful for realistic workloads, isolating write-spikes and ensuring that important caches are not slowed down by increased best-effort traffic.
Original languageEnglish
Title of host publication20th USENIX Conference on File and Storage Technologies (FAST 22)
Place of PublicationSanta Clara, CA
PublisherUSENIX Association
Number of pages16
ISBN (Print)978-1-939133-26-7
Publication statusPublished - 24 Feb 2022
Event20th USENIX Conference on File and Storage Technologies, 2022 - Santa Clara, United States
Duration: 22 Feb 202224 Feb 2022
Conference number: 20


Conference20th USENIX Conference on File and Storage Technologies, 2022
Abbreviated titleFAST 2022
Country/TerritoryUnited States
CitySanta Clara
Internet address


Dive into the research topics of 'NyxCache: Flexible and Efficient Multi-tenant Persistent Memory Caching'. Together they form a unique fingerprint.

Cite this