Trading off logging overhead and coordinating overhead to achieve efficient rollback recovery

Concurrency and Computation: Practice and Experience

Volumn 21, Issue 6, 2009, Pages 819-853

  Yang, Jin Min ^a   Li, Kin Fun ^b   Li, Wen Wei ^a   Zhang, Da Fang ^a  

^a HUNAN UNIVERSITY   (China)

^b UNIVERSITY OF VICTORIA   (Canada)

Author keywords

Coordinating overhead; Logging overhead; Performance optimization; Rollback recovery

Indexed keywords

COMMERCE;

COORDINATED CHECKPOINTING; COORDINATING OVERHEAD; DISTRIBUTED ENVIRONMENTS; LONG-RUNNING APPLICATIONS; MESSAGE LOGGING PROTOCOLS; PERFORMANCE OPTIMIZATIONS; RECOVERY EFFICIENCY; ROLL-BACK RECOVERIES;

RECOVERY;

EID: 65349094006     PISSN: 15320626     EISSN: 15320634     Source Type: Journal    
DOI: 10.1002/cpe.1364     Document Type: Article

References (24)

1. Foster L, Kesselman C. Computational grids. The Grid: Blueprint for a New Computing Infrastructure, Chapter 2. Morgan Kaufmann Publishers: San Francisco, CA, U.S.A., 1999. Available at: http://www.globus.org/research/ papers.html [28 May 2008].
2. Elnozahy E, Alvisi L, Wang Y, Johnson DB. A survey of rollback recovery protocols in message passing systems. ACM Computing Surveys 2002; 33(3):375-408.
3. Cao G, Singhal M. Checkpointing with mutable checkpoints. Theoretical Computer Science 2003; 290:1127-1148.
4. Koo R, Toueg S. Checkpointing and rollback-recovery for distributed systems. IEEE Transactions on Software Engineering 1987; 13(1):23-31.
5. Alvisi L, Marzullo K. Message logging: Pessimistic, optimistic, causal and optimal. IEEE Transactions on Software Engineering 1998; 24(2):149-159.
6. Huang Y, Wang YM. Why optimistic message logging has not been used in telecommunication systems. Twenty-fifth International Symposium on Fault-tolerant Computing (FTCS-25), Pasadena, CA, U.S.A., 1995; 459-463.
7. Rao S, Alvisi L, Vin HM. The cost of recovery in message logging protocols. IEEE Transactions on Knowledge and Data Engineering 2000; 12(2):160-172.
8. Elnozahy EN, Plank JS. Checkpointing for peta-scale systems: A look into the future of practical rollback-recovery. IEEE Transactions on Dependable and Secure Computing 2004; 1(2):97-108.
9. Silva LM, Silva JG. The performance of coordinated and independent checkpointing. Thirteenth International Symposium on Parallel Processing and the 10th Symposium on Parallel and Distributed Processing, San Juan, Puerto Rico, 1999; 280-284.
10. Lamport L. Time, clocks and the ordering of events in a distributed system. Communications of the ACM 1978; 21(7):558-565.
11. Sistla P, Welch JL. Efficient distributed recovery using message logging. ACM Symposium on Principles of Distributed Computing, Edmonton, Alberta, Canada, 1989; 223-238.
12. Lowery A, Russell JR, Goldbery AP. Optimistic failure recovery for very large networks. Symposium on Reliable Distributed Systems, Pisa, Italy, 1991; 66-75.
13. Vaidya NH. Distributed recovery units: A hybrid and adaptive distributed recovery. Technical Report 93-052, Department of Computer Science, Texas A&M University, 1993.
14. Bhatia K, Marzullo K, Alvisi L. Scalable causal message logging for wide-area environment. Concurrency and Computation: Practice and Experience 2003; 15(3):873-889.
15. Monnet S, Morin C, Badrinath R. Hybrid checkpointing for parallel applications in cluster federations. 2004 IEEE International Symposium on Cluster Computing and the Grid (CCGrid'04), Chicago, IL, U.S.A., 2004; 773-782.
16. Yang JM, Li KF, Zhang DF. A coarse-grained pessimistic message logging scheme for improving rollback recovery efficiency. Third IEEE International Symposium on Dependable, Autonomic and Secure Computing (DASC'07), Columbia, MD, U.S.A., 2007.
17. Vaidya NH. A case for two-level recovery schemes. IEEE Transactions on Computers 1998; 47(6):656-666.
18. Plank JS, Thomason MG. Processor allocation and checkpoint interval selection in cluster computing systems. Journal of Parallel and Distributed Computing 2001; 61(11):1570-1590.
19. Vaidya NH. Impact of checkpoint latency on overhead ratio of a checkpointing scheme. IEEE Transactions on Computers 1997; 46(8):942-947.
20. Agbaria A, Attiya H, Friedman R. Quantifying rollback propagation in distributed checkpointing. Journal of Parallel and Distributed Computing 2004; 64(3):370-384.
21. Yang JM, Zhang DF, Yang XD. WINDAR: A multithreaded rollback-recovery toolkit on Windows. Tenth IEEE Pacific Rim Dependable Computing International Symposium (PRDC10), Papeete, Tahiti, French Polynesia, 2004; 395-400.
22. Candea G, Cutler J, Fox A, Doshi R, Garg P, Gowda R. Reducing recovery time in a small recursively restartable system. 2002 International Conference on Dependable Systems and Networks (DSN'02), 2002; 605-614.
23. Plank JS, Elwasif WR. Experimental assessment of workstation failures and their impact on checkpointing systems. Twenty-eighth International Symposium on Fault-tolerant Computing, Munich, Germany, 1998; 48-57.
24. Yang JM, Zhang DF, Yang XD. Reliable user-level rollback recovery implementation for multithreaded processes on Windows. Software-Practice and Experience 2007; 37(3):331-346.