NStore: A High-Performance NUMA-Aware Key-Value Store for Hybrid Memory

Emerging persistent memory (PM) promises near-DRAM performance, larger capacity, and data persistence, attracting researchers to design PM-based key-value stores. However, existing PM-based key-value stores lack awareness of the Non-Uniform Memory Access (NUMA) architecture on PM, where accessing PM on remote NUMA sockets is considerably slower than accessing local PM. This NUMA-unawareness results in sub-optimal performance when scaling on NUMA. Although DRAM caching alleviates this issue, existing cache policies ignore the performance disparity between remote and local PM accesses, keeping remote PM access as a performance bottleneck when scaling PM stores on NUMA. Furthermore, creating hot data views in each socket's PM fails to eliminate remote PM writes and, worse, induces additional local PM writes. This paper presents NStore, a high-performance NUMA-aware key-value store for the PM-DRAM hybrid memory. NStore introduces a NUMA-aware cache replacement strategy, called Remote Access First (RAF) cache in DRAM, to minimize remote PM accesses. In addition, NStore deploys Nlog, a write-optimized log-structured persistent storage, purposed to eliminate remote PM writes. NStore further mitigates the NUMA impacts through localized scan operations, efficient garbage collection, and multi-thread recovery for Nlog. Evaluations show that NStore outperforms state-of-the-art PM-based key-value stores, achieving up to 13.9<inline-formula><tex-math notation="LaTeX">$\times$</tex-math></inline-formula> and 11.2<inline-formula><tex-math notation="LaTeX">$\times$</tex-math></inline-formula> higher write and read throughput, respectively.

Authors

Institutions

Publication Details

Journal
IEEE Transactions on Computers
Published
2024-11-21
DOI
https://doi.org/10.1109/tc.2024.3504269
Citations
3
Primary Topic
Advanced Data Storage Technologies
Type
article
Field-Weighted Citation Impact
1.05
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
article

NStore: A High-Performance NUMA-Aware Key-Value Store for Hybrid Memory

Guokuan Li, Kai Lü, Hong Jiang, Zeyang Zhao et al.
3 citations
IEEE Transactions on Computers
Advanced Data Storage Technologies
1.05
article

NStore: A High-Performance NUMA-Aware Key-Value Store for Hybrid Memory

Guokuan Li, Kai Lü, Hong Jiang, Zeyang Zhao, B. Lai, Changsheng Xie, Zhonghua Wang, Peng Xu, Jiguang Wan
article en
3 citations

Abstract

Emerging persistent memory (PM) promises near-DRAM performance, larger capacity, and data persistence, attracting researchers to design PM-based key-value stores. However, existing PM-based key-value stores lack awareness of the Non-Uniform Memory Access (NUMA) architecture on PM, where accessing PM on remote NUMA sockets is considerably slower than accessing local PM. This NUMA-unawareness results in sub-optimal performance when scaling on NUMA. Although DRAM caching alleviates this issue, existing cache policies ignore the performance disparity between remote and local PM accesses, keeping remote PM access as a performance bottleneck when scaling PM stores on NUMA. Furthermore, creating hot data views in each socket's PM fails to eliminate remote PM writes and, worse, induces additional local PM writes. This paper presents NStore, a high-performance NUMA-aware key-value store for the PM-DRAM hybrid memory. NStore introduces a NUMA-aware cache replacement strategy, called Remote Access First (RAF) cache in DRAM, to minimize remote PM accesses. In addition, NStore deploys Nlog, a write-optimized log-structured persistent storage, purposed to eliminate remote PM writes. NStore further mitigates the NUMA impacts through localized scan operations, efficient garbage collection, and multi-thread recovery for Nlog. Evaluations show that NStore outperforms state-of-the-art PM-based key-value stores, achieving up to 13.9<inline-formula><tex-math notation="LaTeX">$\times$</tex-math></inline-formula> and 11.2<inline-formula><tex-math notation="LaTeX">$\times$</tex-math></inline-formula> higher write and read throughput, respectively.

IEEE Transactions on ComputersVol. 74(3)
The University of Texas at Arlington (US), Zhejiang Lab (CN), Wuhan National Laboratory for Optoelectronics (CN), Huazhong University of Science and Technology (CN)
Affordable and clean energy
Openalex Percentile: Top 20%
Advanced Data Storage Technologies
1.05
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.