Dynamic Affinity Cluster Allocation in a Shared Disks Cluster
Tóm tắt
A shared disks (SD) cluster couples multiple computing nodes for high performance transaction processing, and all nodes share a common database at the disk level. In the SD cluster, a front-end router selects a node for an incoming transaction to be executed. An affinity-based routing can increase the buffer hit ratio of each node by clustering transactions referencing similar data to be executed on the same node. However, the affinity-based routing is non-adaptive to the changes of the system load. This means that a specific node would be overloaded if corresponding transactions rush into the system. In this paper, we propose a new transaction routing algorithm, named Dynamic Affinity Cluster Allocation (DACA). DACA can make an optimal balance between the affinity-based routing and indiscriminate sharing of load in the SD cluster. As a result, DACA can increase the buffer hit ratio and reduce the frequency of inter-node buffer invalidations while achieving the dynamic load balancing.
Tài liệu tham khảo
M. Carey, S. Krishnamurthi, and M. Livny. Load control for locking: the ‘half-and-half’ approach. Proc. 9th ACM PODS, 72–84, (1990).
H. Cho. Database recovery using incomplete page versions in a multisystem data sharing environment. Information Processing Letters, 83(1):49–55, (2002).
H. Cho and J. Park. Maintaining cache coherency in a multisystem data sharing environment. J. Syst. Architecture, 45(4):285–303, (1998).
A. Dan and P. Yu. Performance analysis of buffer coherency policies in a multisystem data sharing environment. IEEE Trans. Parallel and Distributed Systems, 4(3):(1993), 289–305.
DB2 Universal Database for OS/390 and z/OS—Data Sharing: Planning and Administration, IBM SC26-9935–01, (2001).
D. DeWitt and J. Gray. Parallel database systems: the future of high performance database systems. Comm. ACM, 35(6):85–98, (1992).
S. Haldar and D. K. Subramanian. An affinity-based dynamic load balancing protocol for distributed transaction processing systems. Performance Evaluation, 17(1):53–71, (1993).
B. Hamidzadeh, L. Y. Kit, D. J. Lilja. Dynamic task scheduling using online optimization. IEEE Trans. Parallel and Distributed Syst. 11(11):1151–1163, (2000).
V. Kanitkar and A. Delis. Site selection for real-time client request handling. In Proc. 19th Int. Conf. on Distributed Comp. Syst., 298–305, (1999).
T. Kunz. The influence of different workload descriptions on a heuristic load balancing scheme. IEEE Trans. Software Eng., 17(7):725–730, (1991).
C. Mohan and I. Narang. Recovery and coherency control protocols for fast intersystem page transfer and fine-granularity locking in a shared disks transaction environment. In Proc. 17th Int. Conf. on VLDB, 193–207, (1991).
C. N. Nikolaou, M. Marazakis, and G. Georgiannakis. Transaction routing for distributed OLTP systems: survey and recent results. Information Sciences, 97(1–2):45–82, (1997).
E. Rahm. A framework for workload allocation in distributed transaction processing systems. J. Syst. Software, 18(3):171–190, (1992).
H. Schwetmann. User’s Guide of CSIM18 Simulation Engine. Mesquite Software, Inc., (1996).
B. A. Shirazi, A. R. Hurson, and K. M. Kavi. Scheduling and Load Balancing in Parallel and Distributed Systems. IEEE Computer Society Press, (1995).
M. Vallath. Oracle Real Application Clusters. Elsevier Digital Press, (2004).
M. Yousif, Shared-storage clusters, Cluster Comp., 2(4):249–257, (1999).
P. Yu and A. Dan. Performance analysis of affinity clustering on transaction processing coupling architecture. IEEE Trans. Knowledge and Data Eng., 6(5):764–786, (1994).
P. Yu and A. Dan. Performance evaluation of transaction processing coupling architectures for handling system dynamics. IEEE Trans. Parallel and Distributed Syst., 5(2):139–153, (1994).