Abstract
We describe the major features of the completely decentralized adaptive file system MELODY which was designed for realizing anintegrated system design for a distributed real-time system working in a hazardous and unpredictable environment. MELODY's adaptivity mechanisms are based on novel services rendered by the distributed operating system DRAGON SLAYER. The file system, in order to both meet real-time constraints and provide for high availability, allows for replicating, relocating, or deleting file copies. Such copies may also bepublic orprivate. At every site aLocal Task Scheduler tries to schedule the arriving critical tasks, based on the availability of resources at this site such that deadline failures are minimized. Depending on the deadline failure history, status changes as well as file replication, deletion, or relocation are analyzed and managed by the cooperatingLocal File Assigners. In order to analyze MELODY's real-time performance we report on simulation experiments in which its capability of minimizing deadline failures of time-critical tasks was compared to other file system models: an idealbest-case model, abaseline model with no file replication, a file system allowingonly for replication ofprivate copies, and a model which allows forreplication and relocation of public copies only. While the best-case is unrealistic for a distributed implementation, the other models embody only part of MELODY's mechanisms yet have the benefit of a considerably smaller communication overhead. We report on the distributed simulation results which unambiguously show MELODY's superior performance, in addition to the built-in sensitivity to changes in the environment. A DRAGON SLAYER/MELODY prototype has been completed in our labs in order to serve as a distributed real-time testbed in our future work with MELODY.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Alijani, G.S. 1988. Object Mobility in Distributed Computer Systems. Ph.D. Thesis, Wayne State University.
Bhatt, D., Ghonami, A. and Ramanujan, R. 1987. An Instrumented Testbed for Real-Time Systems Development. InProc. of International IEEE Symposium on 8th Real-Time Systems, San Jose, pp. 241–250.
Biyabani, S.R., Stankovic, J.A. and Ramamritham, K. 1988. The Integration of Deadline and Criticalness. InProc. of the International IEEE Symposium on 9th Real-Time Systems, Huntsville, pp. 152–159.
Chu, W.W. and Leung, K.K. 1987. Module Replication and Assignment for Real-Time Distributed Processing Systems. InProc. of the IEEE, vol. 75, pp. 574–562.
Dowdy, L.W. and Foster, D.V. 1982. Comparative Models of the File Assignment Problem.ACM Computing Surveys, vol. 14.
Friedlander, C.B. and Wedde, H.F. 1986. Distributed Processing Under the DRAGON SLAYER Operating System. InProc. of the 15th International IEEE Conference on Parallel Processing, Pheasant Resort, pp. 250–257.
Gopinath, P., Wiley, P. and Schwan, K. 1989. What Price Object? Evaluating a Real-Time Adaptable Object-Based System. InProc. of the 6th IEEE Workshop on Real-Time Operating Systems and Software, Pittsburgh, pp. 29–34.
Gudmunsson, O., Mosse, D., Ko, K.-T., Agrawala, A. and Tripathi, S. 1988.MARUTI: A Platform for Hard Real-Time Applications. InProc. of the 1989 Navy/Univ. of Maryland Workshop on Operating Systems for Mission-Critical Computing, College Park, Maryland, pp. C1–C14.
Haban, D. and Shin, K.G. 1989. Monitoring Distributed Real-Time Systems and its Applications. InProc. of the 6th IEEE Workshop on Real-Time Operating Systems and Software, Pittsburgh, pp. 67–73.
Liu, C.L. and Layland, J.W. Scheduling Algorithms for Multiprogramming in a Hard Real-Time Environment.Journal of the Association for Computing Machinery, vol. 20, pp. 46–61.
Long, D.D. and Carrol, J.L. The Reliability of Regeneration-Based Replica Protocols. InProc. of the 9th International IEEE Conference on Distributed Computing Systems, Newport Beach, pp. 465–473.
Marzullo, K. Concurrency Control for Transactions with Priorities. Carnegie Mellon University, unpublished material.
Muro, S., Ibaraki, T., Miyajima, H. and Hasegawa, T. 1985. Evaluation of the File Redundancy in Distributed Database Systems.IEEE—Trans. on Software Engineering, vol. SE-11.
Noe, J.D. and Anressian, A. 1987. Effectiveness of Replication in Distributed Computer Networks. InProc. of the 7th International IEEE Conference on Distributed Computing Systems, West Berlin, pp. 508–513.
Pu, C. 1986. Replication of Nested Transactions in the EDEN Distributed System. Ph.D. dissertation, University of Washington.
Rajkumar, R., Sha, L. and Lohoczky, J.P. 1989. An Experimental Investigation of Synchronization Protocols. InProc. of the 6th IEEE Workshop on Real-Time Operating Systems and Software, Pittsburgh, pp. 18–45.
Ramamritham, K. and Stankovic, J.S., 1989. Overview of Spring Project.IEEE Real-Time Systems Newsletter, vol. 5, pp. 18–45.
Sha, L., Rajkumar, R. and Lehoczky, J.P. 1987. Priority Inheritance Protocols: An Approach to Real-Time Synchronization.Technical Report CMU-CS-87-181, Computer Science Department, Carnegie Mellon University, Pittsburgh, Pennsylvania.
Son, S. and Cook, R. 1989. Scheduling and Consistency in Real-Time Database Systems. InProc. of the 6th IEEE Workshop on Real-Time Operating Systems and Software, Pittsburgh, pp. 42–45.
Sprunt, B., Lehoczky, J.P. and Sha, L. 1988. Exploiting Unused Periodic Time for Aperiodic Service Using the Extended Priority Exchange Algorithm. InProc. of the 9th Real-Time Systems Symposium, IEEE, Huntsville, AL, pp. 215–258.
Wedde, H.F. 1987. A Graph-Theoretical Model for Designing Fair Distributed Scheduling Algorithms. In Tinhofer/ Schmidt (eds.).Springer Lecture Notes in Computer Science, vol. 246, pp. 204–226.
Wedde, H.F. and Daniels, D.C. 1989. Practicality of Formal Tools for Achieving Transparent Distributed Resource Management. InProc. of the 1989 Phoenix Conference on Computers and Communications, Phoenix, pp. 277–283.
Wedde, H.F., Korel, F., Brown, W.G. and Chen, S. 1989. Transparent Distributed Object Management Under Completely Decentralized Control. InProc. of the 9th International IEEE Conference on Distributed Computing Systems, Newport Beach, pp. 335–342.
Wedde, H.F., Alijani, G.S. Kang, G. and Kim, B-K. 1988. MELODY: A Distributed Real-Time Testbed for Adaptive Systems. InProc. of the 1989 International IEEE Symposium on Real-Time Systems, Huntsville, pp. 112–119.
Wedde, H.F., Alijani, G.S., Baran, D., Kang, G. and Kim, B-K. 1989. Adaptive Real-time File Handling in Local Area Networks. InProc. EUROMICRO '89 Workshop on Real-Time Systems, pp. 153–161.
Wedde, H.F. and Daniels, D.C. 1988. Graph-Theoretical Tools and Their Use in a Practical Operating System Design Case. In H. Goettler, H.J. Schneider (eds.),Springer Lecture Notes in Computer Science, vol. 314, pp. 186–205.
Zhao, W., Ramamritham, K. and Stankovic, J. 1987. Scheduling Tasks with Resource Requirements in Hard Real-Time Systems.IEEE Trans. Software Engineering, vol. SE-13, pp. 564–576.
Author information
Authors and Affiliations
Additional information
This work was partially supported by IBM Endicott (research Agreement No. 6073-86) by the State of Michigan (IMR-87-146751), and by General Dynamics Land Systems (#DEY-605089).
Rights and permissions
About this article
Cite this article
Wedde, H.F., Huizinga, D., Kang, G. et al. MELODY: A completely decentralized adaptive file system for handling real-time tasks in unpredictable environments. Real-Time Syst 2, 347–364 (1990). https://doi.org/10.1007/BF01995677
Issue Date:
DOI: https://doi.org/10.1007/BF01995677