This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Recovery Analysis of Data Sharing Systems under Deferred Dirty Page Propagation Policies
July 1997 (vol. 8 no. 7)
pp. 695-711

Abstract—In a multinode data sharing environment, different buffer coherency control schemes based on various lock retention mechanisms can be designed to exploit the concept of deferring the propagation or writing of dirty pages to disk to improve normal performance. Two types of deferred write polices are considered. One policy only propagates dirty pages to disk at the times when dirty pages are flushed out of the buffer under LRU buffer replacement. The other policy also performs writes at the times when dirty pages are transferred across nodes. The dirty page propagation policy can have significant implications on the database recovery time. In this paper, we provide an analytical modeling framework for the analysis of the recovery times under the two deferred write policies. We demonstrate how these policies can be mapped onto a unified analytic modeling framework. The main challenge in the analysis is to obtain the pending update count distribution which can be used to determine the average numbers of log records and data I/Os needed to be applied during recovery. The analysis goes beyond previous work on modeling buffer hit probability in a data sharing system where only the average buffer composition, not the distribution, needs to be estimated, and recovery analysis in a single node environment where the complexities on tracking the propagation of dirty pages across nodes and the buffer invalidation effect do not appear. A clipping mechanism can be employed to improve recovery time where the number of pending update on a dirty page is limited by forcing a dirty page to disk after the number of updates accumulated on this page exceeds a certain threshold. The analysis captures the effect of clipping also. Finally, we show the sensitivities of the recovery time and normal performance to the clipping count.

[1] P. Biswas, K.K. Ramakrishnan, and D. Towsley, "Trace Driven Analysis of Write Caching Policies for Disks," Proc. 1993 ACM SIGMETRICS Conf. Measurement and Modeling of Computer Systems, pp. 13-23,Santa Clara, Calif., May 1993.
[2] S.B. Behman, T.A. DeNatale, and R.W. Shomler, "Limited Lock Facility in a DASD Control Unit," Technical Report TR 02.859, IBM General Products Division, San Jose, Calif., Oct. 1979.
[3] P. Bernstein, V. Hadzilacos, and N. Goodman, Concurrency Control and Recovery in Database Systems. Addison-Wesley, 1987.
[4] S. Carson and S. Setia, "Analysis of the Periodic Update Write Policy for Disk Cache," IEEE Trans. Software Eng., vol. 18, no. 1, pp. 44-54, Jan. 1992.
[5] D.W. Cornell, D.M. Dias, and P.S. Yu, "On Multisystem Coupling through Function Request Shipping," IEEE Trans. Software Eng., vol. 12, no. 10, pp. 1,006-1,107, Oct. 1986.
[6] A. Dan and P.S. Yu, "Performance Analysis of Buffer Coherency Policies in a Multi-System Data Sharing Environment," IEEE Trans. Parallel and Distributed Systems, vol. 4, no. 3, pp. 289-305, Mar. 1993.
[7] S. Clearwater and F. Provost, "RL4: A Tool for Knowledge-Based Induction," Proc. IEEE Conf. Tools Artificial Intelligence, pp. 24-30, 1990.
[8] A. Dan and P.S. Yu, "Analytic Modeling and Comparison of Buffer Coherency Policies based on Lock Retention," IBM Research Report RC 18664, Yorktown Heights, N.Y., 1993.
[9] A. Dan, P.S. Yu, and J. -Y. Chung, “Characterization of Database Access Pattern for Analytic Prediction of Buffer Hit Probability,” Very Large Database (VLDB) J., vol. 4, pp. 127-154, Jan. 1995.
[10] D.M. Dias, B.R. Iyer, J.T. Robinson, and P.S. Yu, "Integrated Concurrency-Coherency Controls for Multisystem Data Sharing," IEEE Trans. Software Eng., vol. 15, no. 4, pp. 437-448, Apr. 1989.
[11] M. Franklin, M. Zwilling, C. Tan, M. Carey, and D. DeWitt, "Crash Recovery in Client-Server EXODUS," Proc. ACM -SIGMOD Conf.,San Diego, Calif., June 1992.
[12] M.J. Franklin, M.J. Carey, and M. Livny, "Global memory management in client-server DBMS architectures," Proc. 18th VLDB Conf.,Vancouver, Canada, pp. 596-609, 1992.
[13] D. Gawlick and D. Kinkade, "Varieties of Concurrency Control in IMS/VS Fast Path," IEEE Database Eng., vol. 2, no. 8, June 1985.
[14] The Benchmark Handbook for Database and Transaction Processing Systems, J. Gray, ed. San Mateo, Calif.: Morgan Kaufmann, 1991.
[15] T. Haerder and A. Reuter,“Principles of transaction-oriented database recovery,” ACM Computing Surveys, vol. 15, no. 4, pp. 287-317, Dec. 1983.
[16] R.W. Horst and T.C.K. Chow, "An Architecture for High Volume Transaction Processing," Proc. 12th Int'l Symp. Computer Architecture, pp. 240-245,Boston, June 1985.
[17] P. Helland, "The TMF Application Programming Interface: Program to Program Communication, Transactions, and Concurrency in the Tandem NonStop System," Tandem Technical Report TR89.3, Tandem Computers, Feb. 1989.
[18] IBM Corp., "DB2 V2R2 Performance Report," Technical Report GG24-3461, 1989.
[19] IBM Corp., "Sysplex Overview: Introducing Data Sharing and Parallelism in a Sysplex," Technical Report GC28-1208, Apr. 1994.
[20] A. Jhingran and P. Khedkar, "Analysis of Recovery in a Database System Using a Write-Ahead Log Protocol," Proc. ACM SIGMOD Int'l Conf. Management of Data, pp. 175-184,San Diego, Calif., June 1992.
[21] A. Jhingran and P. Khedkar, "Analysis of Run-Time vs. Recovery-Time Tradeoffs for Database Management Systems," IBM Research Report, Yorktown Heights, N.Y., 1992.
[22] N. Kronenberg, H. Levy, and W. Strecker,“VAXcluster: A closely-coupled distributed system,”ACM Trans. Comput. Syst., vol. 4, pp. 130–146, May 1986.
[23] L. Lamport, "Time, clocks and the ordering of events in a distributed system," Comm. ACM, vol. 21, no. 7, pp. 558-565, July 1978.
[24] A. Leff, J. Wolf, and P.S. Yu, "Replication algorithms in a remote caching architecture," IEEE Trans. Parallel and Distributed Systems, vol. 4, no. 11, pp. 1,185-1,204, Nov. 1993.
[25] D. Lomet, "Recovery for Shared Disk Systems using Multiple Redo Logs," DEC Technical Report CRL90/4, Cambridge Research Lab, Mass., Oct. 1990.
[26] C. Mohan personal communication.
[27] C. Mohan, I.S. Narang, and J.D. Palmer, "Page Recovery Using Multiple Logs in a Data Sharing Environment," IBM Technical Disclosure Bulletin, vol. 33, no. 3B, pp. 268-272, 1990.
[28] 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," Proc. 17th VLDB Conf.,Barcelona, Spain, Sept. 1991.
[29] C. Mohan, D. Haderle, B. Lindsay, H. Pirahesh, and P. Schwarz, ARIES: A Transaction Recovery Method Supporting Fine-Granularity Locking and Partial Rollbacks Using Write-Ahead Logging ACM Trans. Database Systems, vol. 17, no. 1, pp. 94-162, Mar. 1992.
[30] C. Mohan, K. Treiber, and R. Obermarck, "Algorithms for the Management of Remote Backup Data Bases for Disaster Recovery," Proc. Ninth Int'l Conf. Data Eng., pp. 511-518,Vienna, Apr. 1993.
[31] C. Polyzois, A. Bhide, and D. Dias, "Disk Mirroring with Alternating Deferred Updates," Proc. 18th Int'l Conf. Very Large Databases, pp. 604-617,Dublin, Aug. 1993.
[32] E. Rahm, "Empirical Performance Evaluation of Concurrency and Coherency Control Protocols for Database Sharing Systems," ACM Trans. Database Systems, vol. 18, no. 2, pp. 333-377, June 1993.
[33] E. Rahm, "Recovery Concepts for Data Sharing Systems," Proc. 17th Int'l Conf. FTCS, pp. 368-375, 1991.
[34] The Tandem Database Group, "NonStop SQL: A Distributed, High Performance, High-Availability Implementation of SQL," Lecture Notes in Computer Science, vol. 359, D. Gawlick, M. Haynie, and A. Reuter, eds. New York: Springer-Verlag, 1989.
[35] J. Teng and R. Gumaer, "Managing IBM Database 2 Buffers to Maximize Performance," IBM Systems J., vol. 24, no. 2, pp. 211-218, 1984.
[36] J.T. Robinson, "A Fast General Purpose Hardware Synchronization Mechanism," SIGMOD Record, pp. 122-130, 1985.
[37] P. Schwarz, "Transactions on Typed Objects," Technical Report CMU-CS-84-166, Carnegie Mellon Univ., Dec. 1984.
[38] A. Spector, R. Pausch, and G. Bruell, "Camelot: A Flexible, Distributed Transaction Processing Systems," Proc. IEEE Compcon Spring '88,San Francisco, Mar. 1988.
[39] P.S. Yu, D.M. Dias, J.T. Robinson, B.R. Iyer, and D.W. Cornell, "On Coupling Multi-Systems Through Data Sharing," Proc. IEEE, vol. 75, no. 5, pp. 573-587, May 1987.
[40] P.S. Yu and A. Dan, "Performance Evaluation of Transaction Processing Coupling Architectures for Handling System Dynamics," IEEE Trans. Parallel and Distributed Systems, vol. 5, no. 2, pp. 139-153, Feb. 1994.
[41] P.S. Yu and A. Dan, "Performance Analysis of Affinity Clustering on Transaction Processing Coupling Architectures," IEEE Trans. Knowledge and Data Eng., vol. 6, no. 5, pp. 764-786, Oct. 1994.

Index Terms:
Recovery analysis, deferred write, coupled systems, analytic modeling, transaction processing, database systems.
Citation:
Asit Dan, Philip S. Yu, Anant Jhingran, "Recovery Analysis of Data Sharing Systems under Deferred Dirty Page Propagation Policies," IEEE Transactions on Parallel and Distributed Systems, vol. 8, no. 7, pp. 695-711, July 1997, doi:10.1109/71.598345
Usage of this product signifies your acceptance of the Terms of Use.