ODTrans: 适用于云数据存储系统的容错的事务协议

doi:10.13209/j.0479-8023.2015.011

北京大学学报（自然科学版）

• 北京大学学报 •

ODTrans: 适用于云数据存储系统的容错的事务协议

程序^1,3;李红燕^2,3;王腾蛟^1,3;杨冬青^1,3

1. 北京大学高可信软件技术教育部重点实验室, 北京 100871;
2. 北京大学机器感知与智能教育部重点实验室, 北京 100871;
3. 北京大学信息科学技术学院, 北京 100871;

收稿日期:2014-02-11 修回日期:2014-03-18 出版日期:2015-05-20 发布日期:2015-05-20
通讯作者: 杨冬青 dqyang@pku.edu.cn

ODTrans: Fault Tolerant Transaction Protocols for the Cloud Data Store

CHENG Xu^1,3;LI Hongyan^2,3;WANG Tengjiao^1,3;YANG Dongqing^1,3

1. Key Laboratory of High Confidence Software Technologies (MOE), Peking University, Beijing 100871;
2. Key Laboratory of Machine Perception (MOE), Peking University, Beijing 100871;
3. School of Electronics Engineering and Computer Science, Peking University, Beijing 100871;

Received:2014-02-11 Revised:2014-03-18 Online:2015-05-20 Published:2015-05-20
Contact: YANG Dongqing dqyang@pku.edu.cn

摘要/Abstract

摘要： 云数据存储系统中, 由于数据的分片、冗余存储以及频繁的节点故障, 导致分布式事务的原子提交问题发生变化, 使得原先的两阶段提交协议(2PC)不再适用。作者对云存储中事务提交的典型场景进行刻画, 重新定义分布式事务的提交问题, 并提出基于一致性协议的方法ODTrans, 用于处理分布式提交和副本更新。相比于传统的2PC 和主备复制方法, 在一个没有拜占庭将军问题的集群中, 它可以始终取得进展。实验结果表明, 所提方法可以获得与已有的方法相近的性能, 既可以容忍从节点发生错误, 也可以应对主节点的故障。

关键词: 分布式事务, 容错性, 云数据存储

Abstract: When it comes to the cloud data store, due to data segmentation, multiple copies of each division and frequent node failures, the problem of atomic commitment of distributed transactions has changed, and the two-phase commitment protocol (2PC) is no longer fit for it. Therefore, the authors describe the typical scene and redefine the problem. A consensus-based approach, called ODTrans, is proposed to deal with distributed commitment and replicas update separately. Compared with the traditional 2PC and the primary-backup scheme, it could make progress all the while in a cluster without the Byzantine Generals Problem. Experimental results demonstrate that proposed method not only could achieve performance close to the state-of-the-art method but also is able to tolerate the faults of both master and slaves.

Key words: distributed transaction, fault tolerance, cloud data store

程序;李红燕;王腾蛟;杨冬青. ODTrans: 适用于云数据存储系统的容错的事务协议[J]. 北京大学学报（自然科学版）, DOI: 10.13209/j.0479-8023.2015.011.

CHENG Xu;LI Hongyan;WANG Tengjiao;YANG Dongqing. ODTrans: Fault Tolerant Transaction Protocols for the Cloud Data Store[J]. Acta Scientiarum Naturalium Universitatis Pekinensis, DOI: 10.13209/j.0479-8023.2015.011.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: https://xbna.pku.edu.cn/CN/10.13209/j.0479-8023.2015.011

https://xbna.pku.edu.cn/CN/Y2015/V51/I3/398

参考文献

[1] Das S, Agrawal D, Abbadi A E. G-store: a scalable data store for transactional multi key access in the cloud // Proceedings of the 1st ACM Symposium on Cloud Computing. New York: ACM, 2010: 163–174
[2] Vogels W. Eventually consistent. Communications of the ACM. New York: ACM, 2009, 52(1): 40–44
[3] Brewer E. CAP twelve years later: how the “rules” have changed. Computer, 2012, 45(2): 23–29
[4] Mahajan P, Alvisi L, Dahlin M. Consistency, availability, and convergence. Technical Report 北京大学学报(自然科学版) 第51 卷第3 期 2015 年5 月 408 TR-11-22. Austin: Computer Science Department, University of Texas at Austin, 2011
[5] Peng D, Dabek F. Large-scale incremental processing using distributed transactions and notifications // Proceedings of the 9th USENIX Conference on Operating Systems Design and Implementation. Berkeley: USENIX Association, 2010: 1–15
[6] Williams D. Locking and transactions over Cassandra using Cages [DB/OL]. (2010–05–12)[2012–07–11]. http://ria101.wordpress.com/2010/05/12/locking-andtransactions- over-cassandra-using-cages
[7] Rao J, Shekita E J, Tata S. Using Paxos to build a scalable, consistent, and highly available datastore. Proceedings of the VLDB Endowment, 2011, 4(4): 243–254
[8] Kraska T, Pang G, Franklin M J, et al. MDCC: multi-data center consistency // Proceedings of the Eurosys’13. Prague, 2013: 113–126
[9] Baker J, Bond C, Corbett J, et al. Megastore: providing scalable, highly available storage for interactive services // Proceedings of the CIDR. Asilomar, 2011: 223–234
[10] Schütt T, Schintke F, Reinefeld A. Scalaris: reliable transactional P2P key/value store // Proceedings of the 7th ACM SIGPLAN Workshop on ERLANG. New York: ACM, 2008: 41–48
[11] Thomson A, Abadi D J. The case for determinism in database systems. Proceedings of the VLDB Endowment, 2010, 3: 70–80
[12] Zhang C, De Sterck H. HBaseSI: multi-row distributed transactions with global strong snapshot isolation on clouds. Scalable Computing: Practice and Experience, 2011, 12(2): 209–226
[13] Aguilera M K, Merchant A, Shah M, et al. Sinfonia: a new paradigm for building scalable distributed systems. Proceedings of the the 21st ACM SIGOPS Symposium on Operating Systems Principles, 2007, 41(6): 159–174
[14] Corbett J C, Dean J, Epstein M, et al. Spanner: Google’s globally-distributed database // Proceedings of the OSDI. Hollywood, CA, 2012: 251–264
[15] Abadi D. Consistency tradeoffs in modern distributed database system design: CAP is only part of the story. Computer, 2012, 45(2): 37–42 [16] Lamport L. The part-time parliament. ACM Transactions on Computer Systems (TOCS), 1998, 16(2): 133–169
[17] Gray J, Lamport L. Consensus on transaction commit. ACM Transactions on Database Systems (TODS), 2006, 31(1): 133–160
[18] Cooper B F, Silberstein A, Tam E, et al. Benchmarking cloud serving systems with YCSB // Proceedings of the 1st ACM Symposium on Cloud Computing. New York: ACM, 2012: 143–154

ODTrans: 适用于云数据存储系统的容错的事务协议

ODTrans: Fault Tolerant Transaction Protocols for the Cloud Data Store

PDF

PDF (翻译版)

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 0

编辑推荐

Metrics

留言