High-availability in-memory key-value store using RDMA and Optane DCPMM

被引：3

作者：

Qi, Xuecheng ^{[1
]}

Hu, Huiqi ^{[1
]}

Guo, Jinwei ^{[1
]}

Huang, Chenchen ^{[1
]}

Zhou, Xuan ^{[1
]}

Xu, Ning ^{[2
]}

Fu, Yu ^{[2
]}

Zhou, Aoying ^{[1
]}

机构：

[1] East China Normal Univ, Sch Data Sci & Engn, Shanghai 200062, Peoples R China

[2] China Construct Bank Financial Technol Co Ltd, Shanghai 200120, Peoples R China

来源：

FRONTIERS OF COMPUTER SCIENCE | 2023年 / 17卷 / 01期

关键词：

Data persistence - High availability - Key-value stores - Memory keys - Performance - Remote data - Round trip - Write amplifications;

D O I：

10.1007/s11704-022-1123-8

中图分类号：

TP [自动化技术、计算机技术];

学科分类号：

0812 ;

摘要：

In this paper, we propose a fast high-availability in-memory key-value store based on RDMA network and Optane DCPMM named FaHA. FaHA proposes RDMA persist PRC that enables remote data persistence for fast log shipping with minimal round-trip and persistence overhead. FaHA further designs append-only storage with pipeline batching scheme in NVM and a hotness-aware differential hash index in DRAM to relieve read/write amplification of Optane DCPMM. Evaluations show that FaHA supports up to 2–3 synchronous backups without significantly lowering the primary’s performance, and outperforms existing works.

引用

页数：3

共 50 条

[11] Improving Memory Access Performance of In-Memory Key-Value Store Using Data Prefetching Techniques
Zhu, PengFei
Sun, GuangYu
Wang, Peng
Chen, MingYu
ADVANCED PARALLEL PROCESSING TECHNOLOGIES, APPT 2015, 2015, 9231 : 1 - 17
[12] A High-performance RDMA-oriented Learned Key-value Store for Disaggregated Memory Systems
Li, Pengfei
Hua, Yu
Zuo, Pengfei
Chen, Zhangyu
Sheng, Jiajie
ACM TRANSACTIONS ON STORAGE, 2023, 19 (04)
[13] CubicRing: Exploiting Network Proximity for Distributed In-Memory Key-Value Store
Zhang, Yiming
Li, Dongsheng
Guo, Chuanxiong
Wu, Haitao
Xiong, Yongqiang
Lu, Xicheng
IEEE-ACM TRANSACTIONS ON NETWORKING, 2017, 25 (04) : 2040 - 2053
[14] Cache-Conscious Data Placement in an In-Memory Key-Value Store
Tinnefeld, Christian
Zeier, Alexander
Plattner, Hasso
PROCEEDINGS OF THE 15TH INTERNATIONAL DATABASE ENGINEERING & APPLICATIONS SYMPOSIUM (IDEAS '11), 2011, : 134 - 142
[15] KVSEV: A Secure In-Memory Key-Value Store with Secure Encrypted Virtualization
You, Junseung
Lee, Kyeongryong
Moon, Hyungon
Cho, Yeongpil
Paek, Yunheung
PROCEEDINGS OF THE 2023 ACM SYMPOSIUM ON CLOUD COMPUTING, SOCC 2023, 2023, : 233 - 248
[16] FastStore: A High-Performance RDMA-enabled Distributed Key-Value Store with Persistent Memory
Xiong, Ziwei
Jiang, Dejun
Xiong, Jin
2023 IEEE 43RD INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS, ICDCS, 2023, : 406 - 417
[17] ZipKV: In-Memory Key-Value Store with Built-In Data Compression
Ma, Linsen
Xie, Rui
Zhang, Tong
PROCEEDINGS OF THE 2023 ACM SIGPLAN INTERNATIONAL SYMPOSIUM ON MEMORY MANAGEMENT, ISMM 2023, 2023, : 150 - 162
[18] HydraDB: A Resilient RDMA-driven Key-Value Middleware for In-Memory Cluster Computing
Wang, Yandong
Zhang, Li
Tan, Jian
Li, Min
Gao, Yuqing
Guerin, Xavier
Meng, Xiaoqiao
Meng, Shicong
PROCEEDINGS OF SC15: THE INTERNATIONAL CONFERENCE FOR HIGH PERFORMANCE COMPUTING, NETWORKING, STORAGE AND ANALYSIS, 2015,
[19] Nessie: A Decoupled, Client-Driven Key-Value Store Using RDMA
Cassell, Benjamin
Szepesi, Tyler
Wong, Bernard
Brecht, Tim
Ma, Jonathan
Liu, Xiaoyi
IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2017, 28 (12) : 3537 - 3552
[20] KV-Direct: High-Performance In-Memory Key-Value Store with Programmable NIC
Li, Bojie
Ruan, Zhenyuan
Xiao, Wencong
Lu, Yuanwei
Xiong, Yongqiang
Putnam, Andrew
Chen, Enhong
Zhang, Lintao
PROCEEDINGS OF THE TWENTY-SIXTH ACM SYMPOSIUM ON OPERATING SYSTEMS PRINCIPLES (SOSP '17), 2017, : 137 - 152

← 1 2 3 4 5 →