PaxosStore: High-availability Storage Made Practical in WeChat

被引:25
|
作者
Zheng, Jianjun [1 ]
Lin, Qian [1 ,2 ]
Xu, Jiatao [1 ]
Wei, Cheng [1 ]
Zeng, Chuwei [1 ]
Yang, Pingan [1 ]
Zhang, Yunfan [1 ]
机构
[1] Tencent Inc, Shenzhen, Peoples R China
[2] Natl Univ Singapore, Singapore, Singapore
来源
PROCEEDINGS OF THE VLDB ENDOWMENT | 2017年 / 10卷 / 12期
关键词
TIME; CONSENSUS;
D O I
10.14778/3137765.3137778
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 present PaxosStore, a high-availability storage system developed to support the comprehensive business of WeChat. It employs a combinational design in the storage layer to engage multiple storage engines constructed for different storage models. PaxosStore is characteristic of extracting the Paxos-based distributed consensus protocol as a middleware that is universally accessible to the underlying multi-model storage engines. This facilitates tuning, maintaining, scaling and extending the storage engines. According to our experience in engineering practice, to achieve a practical consistent read/write protocol is far more complex than its theory. To tackle such engineering complexity, we propose a layered design of the Paxos-based storage protocol stack, where PaxosLog, the key data structure used in the protocol, is devised to bridge the programmingoriented consistent read/write to the storage- riented Paxos procedure. Additionally, we present optimizations based on Paxos that made fault-tolerance more efficient. Discussion throughout the paper primarily focuses on pragmatic solutions that could be insightful for building practical distributed storage systems.
引用
收藏
页码:1730 / 1741
页数:12
相关论文
共 50 条
  • [41] High-availability algorithms for distributed stream processing
    Hwang, JH
    Balazinska, M
    Rasin, A
    Çetintemel, U
    Stonebraker, M
    Zdonik, S
    ICDE 2005: 21ST INTERNATIONAL CONFERENCE ON DATA ENGINEERING, PROCEEDINGS, 2005, : 779 - 790
  • [42] High-availability systems bypass bus traffic
    Stevenson, A
    EDN, 2001, 46 (11) : 82 - 82
  • [43] High-Availability Computing Platform with Sensor Fault Resilience
    Lee, Yen-Lin
    Arizky, Shinta Nuraisya
    Chen, Yu-Ren
    Liang, Deron
    Wang, Wei-Jen
    SENSORS, 2021, 21 (02) : 1 - 16
  • [44] High-availability server platform for IP communication services
    Kimura, N
    Yamada, A
    Seshake, H
    Nishizono, T
    ELECTRONICS AND COMMUNICATIONS IN JAPAN PART I-COMMUNICATIONS, 2006, 89 (06): : 41 - 50
  • [45] Security log time synchronization for high-availability systems
    Naedele, M
    INDIN 2003: IEEE INTERNATIONAL CONFERENCE ON INDUSTRIAL INFORMATICS, PROCEEDINGS, 2003, : 199 - 206
  • [46] Availability requirement for a fault-management server in high-availability communication systems
    Sun, HR
    Han, JJ
    Levendel, H
    IEEE TRANSACTIONS ON RELIABILITY, 2003, 52 (02) : 238 - 244
  • [47] A Deployment Management of High-Availability Microservices for Edge Computing
    Chen, Hung-Ming
    Chen, Shih-Ying
    Zheng, Zhong-Xiang
    Huang, Ti-Wei
    Huang, Cheng-Yu
    2020 INTERNATIONAL SYMPOSIUM ON COMPUTER, CONSUMER AND CONTROL (IS3C 2020), 2021, : 110 - 113
  • [48] High-availability clusters: A taxonomy, survey, and future directions
    Somasekaram, Premathas
    Calinescu, Radu
    Buyya, Rajkumar
    JOURNAL OF SYSTEMS AND SOFTWARE, 2022, 187
  • [49] High-availability VoD system with dynamic fault tolerant
    School of Electronics and Information Engineering, Xi'an Jiaotong University, Xi'an 710049, China
    不详
    Jisuanji Gongcheng, 2006, 10 (86-88):
  • [50] Towards a Bayesian Prognostic Framework for High-Availability Clusters
    Somasekaram, Premathas
    Calinescu, Radu
    COMPANION PROCEEDINGS OF THE 14TH IEEE/ACM INTERNATIONAL CONFERENCE ON UTILITY AND CLOUD COMPUTING (UCC'21 COMPANION), 2021,