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 31 条
  • [21] Exploring Memory Access Similarity to Improve Irregular Application Performance for Distributed Hybrid Memory Systems
    Liu, Wenjie
    He, Xubin
    Liu, Qing
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2023, 34 (03) : 797 - 809
  • [22] Alter: Towards Optimizing Persistent Indexes in Hybrid Memory Systems
    Xu, Ziyue
    Cui, Lixiao
    Wang, Gang
    Liu, Xiaoguang
    19TH IEEE INTERNATIONAL SYMPOSIUM ON PARALLEL AND DISTRIBUTED PROCESSING WITH APPLICATIONS (ISPA/BDCLOUD/SOCIALCOM/SUSTAINCOM 2021), 2021, : 308 - 315
  • [23] A Hybrid Approach for Managing Data Pages in Persistent Memory File Systems
    Chen Y.
    Zhu B.
    Han Y.
    Tu Y.
    Shu J.
    Shu, Jiwu (shujw@tsinghua.edu.cn), 1600, Science Press (57): : 281 - 290
  • [24] FairHym: Improving Inter-Process Fairness on Hybrid Memory Systems
    Imamura, Satoshi
    Yoshida, Eiji
    2020 9TH IEEE NON-VOLATILE MEMORY SYSTEMS AND APPLICATIONS SYMPOSIUM (NVMSA 2020), 2020, : 13 - 18
  • [25] Pointer Analysis for Programs on Hybrid DRAM-PM Memory Systems
    Lee, Ruey-Heng
    Chen, Peng-Sheng
    PROCEEDINGS OF THE 52ND INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING WORKSHOPS PROCEEDINGS, ICPP-W 2023, 2023, : 96 - 103
  • [26] TLB Coalescing for Multi-Grained Page Migration in Hybrid Memory Systems
    Wang, Xiaoyuan
    Liu, Haikun
    Liao, Xiaofei
    Jin, Hai
    Zhang, Yu
    IEEE ACCESS, 2020, 8 : 66304 - 66314
  • [27] Contour: A Process Variation Aware Wear-Leveling Mechanism for Inodes of Persistent Memory File Systems
    Chen, Xianzhang
    Sha, Edwin H. -M.
    Wang, Xinxin
    Yang, Chaoshu
    Jiang, Weiwen
    Zhuge, Qingfeng
    IEEE TRANSACTIONS ON COMPUTERS, 2021, 70 (07) : 1034 - 1045
  • [28] WMAlloc: A Wear-Leveling-Aware Multi-Graine Allocator for Persistent Memory File Systems
    Nie, Shun
    Yang, Chaoshu
    Zhang, Runyu
    Wang, Wenbin
    Liu, Duo
    Chen, Xianzhang
    2020 IEEE 26TH INTERNATIONAL CONFERENCE ON PARALLEL AND DISTRIBUTED SYSTEMS (ICPADS), 2020, : 510 - 517
  • [29] An efficient wear-leveling-aware multi-grained allocator for persistent memory file systems
    Yu, Zhiwang
    Zhang, Runyu
    Yang, Chaoshu
    Nie, Shun
    Liu, Duo
    FRONTIERS OF INFORMATION TECHNOLOGY & ELECTRONIC ENGINEERING, 2023, 24 (05) : 688 - 702
  • [30] PM-Migration: A Page Placement Mechanism for Real-Time Systems with Hybrid Memory Architecture
    Xu, Lidang
    Chen, Gengbin
    Li, Dingding
    Luo, Haoyu
    ALGORITHMS AND ARCHITECTURES FOR PARALLEL PROCESSING, ICA3PP 2023, PT V, 2024, 14491 : 313 - 324