Redundant Task-Allocation in Multicomputer Systems

Vladimir Cherkassky, Chien In Henry Chen

Research output: Contribution to journalArticlepeer-review

7 Scopus citations

Abstract

This paper describes a simple yet effective method to improve multicomputer/multiprocessor system reliability via redundant allocation of tasks to computers (processors). Given any known (nonredundant) scheduling strategy, tasks are allocated to processors statically and redundantly using k-circular shifting (kCS) algorithm, so that if some processors fail during the execution, all tasks can be completed on the remaining processors (but at a longer time). Due to static pre-allocation of tasks this method is simpler and thus more practical than wellknown dynamic reconfiguration and rollback recovery techniques in multiprocessor systems. We discuss in detail redundant allocation of independent tasks to identical processors (computers), subject to real-time constraints on total execution time, and derive analytic reliability estimates for this case. The Longest Processing Time scheduling is given as an example of nonredundant deterministic scheduling for independent tasks. Finally, we discuss processor utilization for redundant task-allocation, and compare it with standby redundancy; our kCS algorithm achieves much higher processor utilization than standby redundancy.

Original languageEnglish (US)
Pages (from-to)336-342
Number of pages7
JournalIEEE Transactions on Reliability
Volume41
Issue number3
DOIs
StatePublished - Sep 1992

Keywords

  • Graceful degradation
  • Multiprocessor system
  • Processor utilization
  • Redundant task-allocation
  • Reliability prediction

Fingerprint

Dive into the research topics of 'Redundant Task-Allocation in Multicomputer Systems'. Together they form a unique fingerprint.

Cite this