Dalio: In-Kernel Centralized Replication for Key-Value Stores

被引:0
|
作者
Kim, Gyuyeong [1 ]
机构
[1] Sungshin Womens Univ, Dept Comp Engn, Seoul, South Korea
关键词
networking stacks; replication protocol; in-kernel acceleration;
D O I
10.1587/transinf.2024EDL8060
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Replication is commonly used in distributed key-value stores for high availability. Recent works show that centralized replication provides high throughput through low-overhead write coordination and consistency-aware read forwarding. Unfortunately, they rely on specialized hardware, which is deploy-challenging and poses various limitations. To this end, we present Dalio, a software-based centralized replication system that does not require extra hardware while supporting high throughput. Our key idea is to offload the replication function to per-shard load balancers with eBPF, an emerging kernel-native technique. By building a replication coordinator with eBPF, we can avoid burdensome kernel networking stack overhead. Our experimental results show that Dalio achieves throughput better than the vanilla Linux by up to 2.05x and is comparable to a hardware-based solution.
引用
收藏
页码:157 / 160
页数:4
相关论文
共 50 条
  • [21] FloDB: Unlocking Memory in Persistent Key-Value Stores
    Balmau, Oana
    Guerraoui, Rachid
    Trigonakis, Vasileios
    Zablotchi, Igor
    PROCEEDINGS OF THE TWELFTH EUROPEAN CONFERENCE ON COMPUTER SYSTEMS (EUROSYS 2017), 2017, : 80 - 94
  • [22] Quantitative Analysis of Consistency in NoSQL Key-Value Stores
    Liu, Si
    Nguyen, Son
    Ganhotra, Jatin
    Rahman, Muntasir Raihan
    Gupta, Indranil
    Meseguer, Jose
    QUANTITATIVE EVALUATION OF SYSTEMS, 2015, 9259 : 228 - 243
  • [23] Interval Indexing and Querying on Key-Value Cloud Stores
    Sfakianakis, George
    Patlakas, Ioannis
    Ntarmos, Nikos
    Triantafillou, Peter
    2013 IEEE 29TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE), 2013, : 805 - 816
  • [24] Evaluation of Key-Value Stores for Distributed Locking Purposes
    Grzesik, Piotr
    Mrozek, Dariusz
    BEYOND DATABASES, ARCHITECTURES AND STRUCTURES (BDAS): PAVING THE ROAD TO SMART DATA PROCESSING AND ANALYSIS, 2019, 1018 : 70 - 81
  • [25] Exploiting key-value data stores scalability for HPC
    Cugnasco, Cesare
    Becerra, Yolanda
    Torres, Jordi
    Ayguade, Eduard
    2017 46TH INTERNATIONAL CONFERENCE ON PARALLEL PROCESSING WORKSHOPS (ICPPW), 2017, : 85 - 94
  • [26] Customizable Scale-Out Key-Value Stores
    Anwar, Ali
    Cheng, Yue
    Huang, Hai
    Han, Jingoo
    Sim, Hyogi
    Lee, Dongyoon
    Douglis, Fred
    Butt, Ali R.
    IEEE TRANSACTIONS ON PARALLEL AND DISTRIBUTED SYSTEMS, 2020, 31 (09) : 2081 - 2096
  • [27] Private Search on Key-Value Stores with Hierarchical Indexes
    Hu, Haibo
    Xu, Jianliang
    Xu, Xizhong
    Pei, Kexin
    Choi, Byron
    Zhou, Shuigeng
    2014 IEEE 30TH INTERNATIONAL CONFERENCE ON DATA ENGINEERING (ICDE), 2014, : 628 - 639
  • [28] Tee-based key-value stores: a survey
    Ait Messaoud, Aghiles
    Ben Mokhtar, Sonia
    Simonet-Boulogne, Anthony
    VLDB JOURNAL, 2025, 34 (01):
  • [29] Coupling Decentralized Key-Value Stores with Erasure Coding
    Cheng, Liangfeng
    Hu, Yuchong
    Lee, Patrick P. C.
    PROCEEDINGS OF THE 2019 TENTH ACM SYMPOSIUM ON CLOUD COMPUTING (SOCC '19), 2019, : 377 - 389
  • [30] Taming Tail Latency in Key-Value Stores: A Scheduling Perspective
    Ben Mokhtar, Sonia
    Canon, Louis-Claude
    Dugois, Anthony
    Marchal, Loris
    Riviere, Etienne
    EURO-PAR 2021: PARALLEL PROCESSING, 2021, 12820 : 136 - 150