SwapKV: A Hotness Aware In-Memory Key-Value Store for Hybrid Memory Systems

被引:3
|
作者
Cui, Lixiao [1 ]
He, Kewen [1 ]
Li, Yusen [1 ]
Li, Peng [2 ]
Zhang, Jiachen [1 ]
Wang, Gang [1 ]
Liu, Xiaoguang [1 ]
机构
[1] Nankai Univ, Coll Comp Sci, Nankai Baidu Joint Lab, TJ Key Lab NDST, Tianjin 300350, Peoples R China
[2] ByteDance Inc, Beijing 100089, Peoples R China
基金
美国国家科学基金会;
关键词
Key-value system; persistent memory; hybrid memory system;
D O I
10.1109/TKDE.2021.3077264
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In-memory Key-Value (KV) stores are widely deployed in modern data centers. These systems generally use DRAM as their storage medium, causing huge hardware costs. The emerging persistent memory (PMEM) is a potential substitute for DRAM, which has a lower price and larger capacity, but lower access speed and bandwidth. Many prior studies strive to build hybrid memory systems to retain both the advantages of DRAM and PMEM. However, they are either application agnostic or simply take DRAM as a cache, which are both not efficient for in-memory KV stores. In this paper, we propose SwapKV, a well-designed in-memory KV store for hybrid DRAM-PMEM system. SwapKV has several promising properties. First, SwapKV combines DRAM and PMEM to a uniform memory pool and only stores one copy of data, which maximizes capacity utilization. Second, SwapKV maps all writing operations to DRAM and migrates data to PMEM with large blocks asynchronously, which mitigates the intrinsic inefficiency of PMEM for writing operations. Third, SwapKV maintains the hot data in DRAM through an efficient hotness filtering and data swapping mechanism, which ensures high system throughput and responsiveness. We implement SwapKV and evaluate it under various workload patterns. The results demonstrate that SwapKV improves the throughput by 11 similar to 41 percent compared to the state-of-the-art alternatives.
引用
收藏
页码:917 / 930
页数:14
相关论文
共 50 条
  • [21] High-availability in-memory key-value store using RDMA and Optane DCPMM
    Qi, Xuecheng
    Hu, Huiqi
    Guo, Jinwei
    Huang, Chenchen
    Zhou, Xuan
    Xu, Ning
    Fu, Yu
    Zhou, Aoying
    FRONTIERS OF COMPUTER SCIENCE, 2023, 17 (01)
  • [22] High-availability in-memory key-value store using RDMA and Optane DCPMM
    Xuecheng Qi
    Huiqi Hu
    Jinwei Guo
    Chenchen Huang
    Xuan Zhou
    Ning Xu
    Yu Fu
    Aoying Zhou
    Frontiers of Computer Science, 2023, 17
  • [23] Catalyst: Optimizing Cache Management for Large In-memory Key-value Systems
    Wang, Kefei
    Chen, Feng
    PROCEEDINGS OF THE VLDB ENDOWMENT, 2023, 16 (13): : 4339 - 4352
  • [24] Efficient Software Rejuvenation of In-memory Key-Value Storages
    Jumonji, Yuto
    Yamada, Hiroshi
    2017 IEEE 28TH INTERNATIONAL SYMPOSIUM ON SOFTWARE RELIABILITY ENGINEERING WORKSHOPS (ISSREW 2017), 2017, : 280 - 285
  • [25] ShieldStore: Shielded In-memory Key-value Storage with SGX
    Kim, Taehoon
    Park, Joongun
    Woo, Jaewook
    Jeon, Seungheun
    Huh, Jaehyuk
    PROCEEDINGS OF THE FOURTEENTH EUROSYS CONFERENCE 2019 (EUROSYS '19), 2019,
  • [26] Fast In-Memory Key-Value Cache System with RDMA
    Ghen, Wei
    Yu, Songping
    Wang, Zhiying
    JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2019, 28 (05)
  • [27] ChameleonDB: a Key-value Store for Optane Persistent Memory
    Zhang, Wenhui
    Zhao, Xingsheng
    Jiang, Song
    Jiang, Hong
    PROCEEDINGS OF THE SIXTEENTH EUROPEAN CONFERENCE ON COMPUTER SYSTEMS (EUROSYS '21), 2021, : 194 - 209
  • [28] Size-aware Sharding For Improving Tail Latencies in In-memory Key-value Stores
    Didona, Diego
    Zwaenepoel, Willy
    PROCEEDINGS OF THE 16TH USENIX SYMPOSIUM ON NETWORKED SYSTEMS DESIGN AND IMPLEMENTATION, 2019, : 79 - 93
  • [29] S3: A Scalable In-memory Skip-List Index for Key-Value Store
    Zhang, Jingtian
    Wu, Sai
    Tan, Zeyuan
    Chen, Gang
    Cheng, Zhushi
    Cao, Wei
    Gao, Yusong
    Feng, Xiaojie
    PROCEEDINGS OF THE VLDB ENDOWMENT, 2019, 12 (12): : 2183 - 2194
  • [30] 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