Buffer management in a real-time shared disks cluster

A great deal of research indicates that the shared disks (SD) cluster is suitable to high performance transaction processing. However, the aggregation of SD cluster with real-time processing has not been investigated. By adopting cluster technology, the real-time services will be highly available and can exploit internode parallelism. In this paper, we consider buffer management issues in a real-time SD cluster. We first propose a real-time buffer coherency algorithm that exploits inherent characteristics of real-time applications and SD cluster. Then we extend traditional buffer replacement algorithms to the real-time SD cluster. They emphasize specific attributes of buffer pages to capitalize locality of references, transaction deadline, and affinity-based routing. We evaluate the performance of the proposed algorithms under a wide variety of transaction workloads and system configurations.

[1]  Herb Schwetman.  CSIM18—the simulation engine , 1996, Winter Simulation Conference.

[2]  Miron Livny,et al.  Priority in DBMS Resource Scheduling , 1989, VLDB.

[3]  Joseph Y.-T. Leung,et al.  Handbook of Real-Time and Embedded Systems , 2007 .

[4]  Haengrae Cho,et al.  Path conscious caching of B+ tree indexes in a shared disks cluster , 2007, J. Parallel Distributed Comput..

[5]  Beng Chin Ooi,et al.  Dynamic buffer management with extensible replacement policies , 2006, The VLDB Journal.

[6]  Philip S. Yu,et al.  Performance Analysis of Affinity Clustering on Transaction Processing Coupling Architecture , 1994, IEEE Trans. Knowl. Data Eng..

[7]  Haengrae Cho,et al.  Feasibility and Performance Study of a Shared Disks Cluster for Real-Time Processing , 2004, AIS.

[8]  Miron Livny,et al.  Data access scheduling in firm real-time database systems , 1992, Real-Time Systems.

[9]  Mazin S. Yousif.  Shared‐storage clusters , 1999, Cluster Computing.

[10]  Alex Delis,et al.  Efficient Processing of Client Transactions in Real-Time , 2004, Distributed and Parallel Databases.

[11]  Murali Vallath.  Oracle Real Application Clusters , 2003 .

[12]  John A. Stankovic,et al.  Buffer Management in Real-Time Databases , 1990 .

[13]  Haengrae Cho,et al.  Dynamic Affinity Cluster Allocation in a Shared Disks Cluster , 2006, The Journal of Supercomputing.

[14]  Anindya Datta,et al.  Buffer management in real-time active database systems , 1998, IEEE Trans. Syst. Man Cybern. Part A.

[15]  Dilip M. Ranade,et al.  Shared Data Clusters: Scaleable, Manageable, and Highly Available Systems (VERITAS Series) , 2002 .

[16]  C. Mohan,et al.  Recovery and Coherency-Control Protocols for Fast Intersystem Page Transfer and Fine-Granularity Locking in a Shared Disks Transaction Environment , 1991, VLDB.

[17]  Tei-Wei Kuo,et al.  Evaluation of concurrency control strategies for mixed soft real-time database systems , 2002, Inf. Syst..

[18]  Sang Hyuk Son,et al.  Real-Time Databases and Data Services , 2004, Real-Time Systems.