Journal of KIISE:Computer Systems and Theory (한국정보과학회논문지:시스템및이론)

Korean Institute of Information Scientists and Engineers (한국정보과학회)
권호 표지

Symmetric Tree Replication Protocol for Efficient Distributed Storage System

효율적인 분산 저장 시스템을 위한 대칭 트리 복제 프로토콜

  • 최성춘 (성균관대학교 정보통신공학부 컴퓨터공학) ;
  • 윤희용 (성균관대학교 정보통신공학부) ;
  • 이강신 (한국정보보호진흥원 기반보호기술팀) ;
  • 이호재 (LG전자 전자기술원)
  • Published : 2004.10.01
Download PDF
⟨ Previous Next ⟩

Abstract

In large distributed systems, replications of data and service are needed to decrease communication cost, increase availability, and avoid single server bottleneck. Tree Quorum protocol is a representative replication protocol, which exploits a logical structure. Tree quorum protocol is one of the replication protocols allowing low read cost only in the best case, while the number of replicas exponentially increases as the level grows. In this paper, thus, we propose a new replication protocol, called symmetric tree protocol which efficiently solves the problem. The proposed symmetric tree protocol also requires much smaller read cost than previous protocols. We conduct cost and availability analysis of the protocols, and the proposed protocol displays comparable read availability to the tree protocol using much smaller number of nodes. Also, the symmetric tree protocol has much smaller response time than the logarithmic protocol.

최근 분산 컴퓨팅 환경에서 데이타와 서비스의 복제는 통신비용의 감소, 데이타 가용성 증가, 그리고 단일 서버의 병목현상을 피하기 위해 필수적이다. 기존의 대표적인 복제 프로토콜로 네트워크를 논리적으로 구성하는 Tree quorum 프로토콜과 Grid프로토콜이 있다. Tree quorum프로토콜은 최선의 경우 가장 우수한 읽기 성능을 보이는 반면 트리의 높이가 증가할수록 노드의 수가 기하급수적으로 증가한다는 단점을 가지고 있다. Grid프로토콜은 읽기 동작에 있어 높은 가용성을 가지는 반면 고장이 없는 환경에서도 같은 읽기 및 쓰기 성능을 보이는 단점을 가지고 있다. 따라서 본 논문에서는 기존의 복제 프로토콜이 가지는 문제점을 해결하고, 대칭적 트리 구조를 이용하여 노드의 장애가 발생하는 환경에서도 우수한 성능을 갖는 복제 프로토콜을 제안한다. 제안된 복제 프로토콜은 Tree quorum 프로토콜에 비해 적은 저기 비용을 가지며, 적은 수의 노드 구성 환경에서도 높은 읽기 가용성을 가진다. 또한 응답시간 면에서도 우수한 성능을 보인다.

Keywords

References

  1. C. Amza., A.L. Cox, W. Zwaenepoel, Data replication strategies for fault tolerance and availability on commodity clusters, Proc. Intl Conf on Dependable Systems and Networks (DSN), 2000, 459-467 https://doi.org/10.1109/ICDSN.2000.857576
  2. H. Y. Youn, B. Krishnarnsetty, D. Lee, B. K. Lee, J. S. Choi, H. G. Kim, C. W. Park, and H. S. Lee, An Efficient Hybrid Replication Protocol for Highly Available Distributed System, Proc. Intl Conf on Communication and Computer Networks (DSN), Nov, 2002
  3. K. Arai, K. Tanaka, M. Takizawa, Group protocol for quorum-based replication, Proc. Seventh Intl Conf on Parallel and Distributed Systems, 2000, 57-64 https://doi.org/10.1109/ICPADS.2000.857683
  4. G. Alonso, Partial Database Replication and Group Communication Primitives, Proc. of the 2nd European Research Seminar on Advances in Distributed Systems (ERSADS97), March 1997, 171-176
  5. P.A. Bernstein and N. Goodman, An Algorithm for Concurrency Control and Recovery in Replicated Distributed Databases, ACM Trans on Distributed Systems, 9(4), 1984, 596-615 https://doi.org/10.1145/1994.2207
  6. R.H. Thomas. A Majority Consensus Approach to Concurrency Control for Multiple Copy Databased, ACM Trans on Database Systems, 4(2),1979, 180-207 https://doi.org/10.1145/320071.320076
  7. D. Davcev, A Dynamic Voting Scheme in Distributed Systems. IEEE Trans on Software Engineering, 15(1), 1989, 93-97 https://doi.org/10.1109/32.21731
  8. D. Saha, S. Rangarajan, S.K. Tripathi, An Analysis of the Average Message Overhead in Replica Control Protocols, IEEE Trans on Parallel and Distributed Systems, 7(10), Oct. 1996, 1026-1034 https://doi.org/10.1109/71.539734
  9. B. Freisleben, H.H. Koch, and O. Theel, Designing Multi-Level Quorum Schemes for Highly Replicated Data. Proc. of the 1991 Pacific Rim Intl Symp on Fault Tolerant Systems, IEEE, 1991, 154-159 https://doi.org/10.1109/{RFTS.1991.212950
  10. D.K. Gifford, Weighted Voting for Replicated Data, Proc. of the 7th ACM Symp on Operating Systems Principles, 1979, 150-162 https://doi.org/10.1145/800215.806583
  11. Lamehamedi, H., Zujun Shentu, Szymanski, R, and Deelman, E., Simulation of dynamic data replication strategies in Data Grids, Proc of the Intl Symp on Parallel and Distributed Processing, 2003, 22-26 https://doi.org/10.1016/j.future.2004.08.001
  12. H. Lamehamedi, B. K. Szymanski, Z.Shentu, and E. Deelman, Data Replication Strategies in Grid Environments, Proc of ICAP'03, 2002, 378-383 https://doi.org/10.1109/ICAPP.2002.1173605
  13. D. Agrawal and A. El Abbadi, The tree Quorum protocol: An Efficient Approach for Managing Replicated Data, Proc of the 16th Very Large Databases (VLDB) Conf, 1990, 243-254
  14. S. Cheung, M. Ammar, and M. Ahamad, The Grid Protocol: A High Performance Scheme for Maintaining Replicated Data, Proc of the 6th Intl Conf on Data Engineering, 1990, 438-445