The KIPS Transactions:PartD (정보처리학회논문지D)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

A Dynamic Transaction Routing Algorithm with Primary Copy Authority

주사본 권한을 이용한 동적 트랜잭션 분배 알고리즘

  • 김기형 (영남대학교 전자정보공학부) ;
  • 조행래 (영남대학교 전자정보공학부) ;
  • 남영환 (쌍용정보통신 IT 솔루션센터 시스템통합 컨설턴트)
  • Published : 2003.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

Database sharing system (DSS) refers to a system for high performance transaction processing. In DSS, the processing nodes are locally coupled via a high speed network and share a common database at the disk level. Each node has a local memory and a separate copy of operating system. To reduce the number of disk accesses, the node caches database pages in its local memory buffer. In this paper, we propose a dynamic transaction routing algorithm to balance the load of each node in the DSS. The proposed algorithm is novel in the sense that it can support node-specific locality of reference by utilizing the primary copy authority assigned to each node; hence, it can achieve better cache hit ratios and thus fewer disk I/Os. Furthermore, the proposed algorithm avoids a specific node being overloaded by considering the current workload of each node. To evaluate the performance of the proposed algorithm, we develop a simulation model of the DSS, and then analyze the simulation results. The results show that the proposed algorithm outperforms the existing algorithms in the transaction processing rate. Especially the proposed algorithm shows better performance when the number of concurrently executed transactions is high and the data page access patterns of the transactions are not equally distributed.

데이터베이스 공유 시스템(Database Sharing System: DSS)은 고성능 트랜잭션 처리를 위해 제안된 시스템이다. DSS에서 고속의 통신망으로 연결된 노드들은 별도의 메모리와 운영체제를 가지며, 데이터베이스를 저장하고 있는 디스크는 모든 노드에 의해 공유된다. 그리고 빈번한 디스크 액세스를 피하기 위해 각 노드는 자신의 메모리 버퍼에 최근에 액세스한 페이지들을 캐싱한다. 본 논문에서는 DSS를 구성하고 있는 각 노드의 부하를 효과적으로 분산한 수 있는 동적 트랜잭션 분배 알고리즘을 제안한다. 제안한 알고리즘은 각 노드에 할당된 주사본 권한을 이용함으로써 노드별 참조 지역성을 지원하고, 그 결과 캐쉬 이용률을 증가하여 디스크 액세스 수를 최소화한다. 뿐만 아니라, 노드의 현재 부하를 고려하여 트랜잭션 분배 정책을 결정함으로써 특정 노드에 트랜잭션이 집중되는 것을 피한다. 제안된 알고리즘의 성능평가를 위해 시뮬레이션 실험을 수행하였으며, 실험결과 제안된 알고리즘이 기존 알고리즘들보다 트랜잭션 처리율에서 높은 성능을 보였다. 특히 트랜잭션 부하량이 높은 경우와 편중된 데이터 참조를 보이는 경우에 좋은 성능을 보였다.

Keywords

References

  1. M. Abdlguerfi and K. Wong (ed.), 'Parallel Databse Techniques,' IEEE Computer Society Press, 1998
  2. A. Dan and P. Yu, 'Performance analysis of Buffer Coherency ,' IEEE Trans. on Parallel and Distributed Syst., Vol.4, No.3, pp.289-305, 1993 https://doi.org/10.1109/71.210812
  3. S. Haldar and D. K. Subramanian, 'An Affinity-based Dynamic Load Balancing Protocol for Distributed Transaction,' Performance Evaluation, Vol.17, No.1, pp.53-71, 1993 https://doi.org/10.1016/0166-5316(93)90012-J
  4. F. Howell and R. Mcnab, 'Simjava Package,' http://www.dcs.ed.ac.uk/home/simjava, April, 1999
  5. L. Miller, A. Hurson andS. Pakzad (ed), 'Parallel Architectures for Data/Knowledge-Based Systems,' IEEE Computer Society Press, 1995
  6. C. Mohan, I. Narang, 'Recovery and Coherency control Protocols for Fast Intersystem Page Transfer and Fine-Granularity Locking in a Shared Disks Transaction Environment,' Proc. Int. Conf. on VLDB pp. 193-207, 1991
  7. K. Ohn, R. Hwang and H. Cho, 'Prototyping PHLOX, A High Performance Transaction Processing System on a Workstation Cluster with Shared Disks,' Proc. 8th IEEE Computer Workshop on FTDCS, pp.67-73, 2001 https://doi.org/10.1109/FTDCS.2001.969624
  8. E. Rahm, 'Primary Copy Synchronization for DB-Sharing,' Info. Syst., Vol.11, No.4, pp.275-286, 1986 https://doi.org/10.1016/0306-4379(86)90008-6
  9. E. Rahm, 'A Framework for Workload Allocation in Distributed Transaction System,' Syst. Soft. Journal, Vol.18, No.3, pp.171-190, 1992 https://doi.org/10.1016/0164-1212(92)90126-5
  10. E. Rahm, 'Empirical Performance Evaluation of Concurrency and Cohereny control Protocols for Database Sharing Systems,' ACM Trans. on Database Syst., Vol. 18, No. 2, pp.333-377, 1993 https://doi.org/10.1145/151634.151639
  11. A. Reuter, 'Load Control and Load Balancing in a Shared Database Management System,' Proc. of 2nd Int. Conf. on Data Eng., pp.188-197, 1986
  12. P. Yu and A. Dan, 'Performance Analysis of Affinity Clustering on Transaction Processing Coupling Architecture,' IEEE Trans. on Knowledge and Data Eng., Vol.6, No.5, pp.764-786, 1994 https://doi.org/10.1109/69.317706
  13. P. Yu and A. Dan, 'Performance Evaluation of Trans,' IEEE Trans. on Parallel and Distributed Syst., Vol.5, No.2, pp.139-153, 1994 https://doi.org/10.1109/71.265942
  14. M. Zaharioudakis, M. Carey and M. Franklin, 'Adaptive, Fine-Grained Sharing in a Client-Server OODBMS : A Callback-Based Approach,' ACM Trans. on Database Syst., Vol.22, No.4, pp.570-627, 1997 https://doi.org/10.1145/278245.278249