Algorithms for scheduling real-time tasks with input error and end-to-end deadlines

Feng, Wu-chun; Liu, J.W.-S.

doi:10.1109/32.585499

Cited by 47 publications

(1 citation statement)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The error-task model in [cFL97] describes scheduling algorithms for preemptive, imprecise, composite real-time tasks. In this model, input error is explicitly accounted for in the design of solution strategies.…”

Section: B Related Workmentioning

confidence: 99%

Totally Clairvoyant Scheduling with Relative Timing Constraints

Subramani¹

2002

View full text Add to dashboard Cite

Public reporting burden for tbis collection of informetion is estimated to overage 1 hour per response, including tlie time for reviewing instructions, si the collection of information. Send comments regerding this burden estimate or any other aspect of this collection of information, including su Operations and Reports, 1215 Jefferson Davis Highway, Suite 1204, Arlington, VA 22202-4302, and to the Office of Management and Budget, PB|. AFRL-SR-AR-TR-03-reviewing iformalian MmVl\mmV1 (Leave blank) REPORT DATE REPORT TYPE AND DATES COVERED01 JAN 02-31 DEC 02 TITLE AND SUBTITLE TOALY CLAIRVOYANT SCHEDULING WITH RELATIVE TIMING CONSTRAINTS AUTHOR(S)K. SUBRAMANI PERFORMING ORGANIZATION NAME(S) AND ADDRESS(ES)WEST VIRGINIA UNIVERSITY MORGANTOWN, WV SPONSORINGIMONITORING AGENCY NAMEIS) AND ADDRESS(ES)AFOSR ABSTRACT IMaximum 200 words)Traditional scheduling models assume that the execution time of a job in a periodic job-set is constant in every instance of its execution. This assumption does not hold m real-time systems wherein job execution time is known to vary. A second feature of traditional models is their lack of expressiveness, in that constraints more complex than precedence constraints (for instance, relative timing constraints) cannot be modeled. Thirdly, the schedulability of a real-time system depends upon the degree of clairvoyance afforded to the dispatcher. In this paper, we shall discuss Totally Clairvoyant Scheduling, as modeled within the E-T-C scheduling framework. We show that instantiation of the scheduling framework capmres the central issues in a real-time flow-shop scheduling problem and design a polynomial time sequential algorithm for the same. We also introduce an error-minimizing performance metric called Violation Degree and establish that optimizing this metric in a Totally Clairvoyant Scheduling System in NP-Hard. . We provide polynomial time algorithms for the case in which the constraints between jobs are strict diff'erence constraints, also called "standard constraints". We also show that a Performance Metric Optimization problem is NP-Hard.[Suba] represents an off'shoot of the main thrust of our work. While working on short refutations for Totally Clairvoyant Scheduling systems, it occurred to us that tree-like resolution refutations of 2SAT formulas could be determined in polynomial time.We have recently proposed the addition of optimization functions to Clairvoyant Scheduling, as well as parallel strategies for large scale problems. This proposal is currently under consideration for funding by AFOSR. AcknowledgementsWe thank Major Juan Vasquez for his encouragement and willingness to explore new ideas in basic research. We hope that the attached papers will vindicate his faith in us. Traditional scheduling models assume that the execution time of a job in a periodic job-set is constant in every instance of its execution. This assumption does not hold in real-time systems wherein job execution time is known to vary. A second feature of traditional models is their lack of expressiven...

show abstract

Section: B Related Workmentioning

confidence: 99%

Totally Clairvoyant Scheduling with Relative Timing Constraints

Subramani¹

2002

View full text Add to dashboard Cite

show abstract

Scheduling real‐time bag‐of‐tasks applications with approximate computations in SaaS clouds

Stavrinides

Karatza

2017

Concurrency and Computation

View full text Add to dashboard Cite

Software as a Service (SaaS) cloud computing has emerged as an attractive platform to tackle various problems of the traditional software distribution model, such as the requirement to acquire and maintain expensive hardware and software infrastructure. SaaS, however, involves many challenges, mainly due to the heterogeneity and multitenancy of the underlying host environment, as well as the nature of the applications executed on such platforms. Applications are usually bags-of-tasks, consisting of independent component tasks that can be executed in any order, featuring different degrees of variability in their computational demands. Furthermore, according to the service level agreement between the cloud provider and the end-users, the execution of such applications must typically complete within a deadline, providing results of acceptable quality.Consequently, one of the most important aspects of SaaS cloud computing is the effective scheduling of multiple parallel applications, avoiding any service level agreement violations. Towards this direction, our contribution in this paper is twofold: (1) We enhance some of the most commonly used scheduling algorithms for bag-of-tasks applications, by utilizing approximate computations, and (2) we investigate the impact of different levels of variability in the computational demands of the applications on the performance of the examined heuristics. KEYWORDSapproximate computations, bags-of-tasks, computational demand variability, performance evaluation, real-time scheduling, SaaS clouds INTRODUCTIONSoftware as a Service (SaaS) cloud computing is becoming a widely adopted paradigm, poised to replace the traditional software distribution model, which requires on-premises software. According to this model, software is provided to the end-users as a service over the Internet, utilizing a particular pricing scheme, such as a pay-as-you-go or a subscription-based approach. SaaS provides better operational efficiency, by eliminating the requirement for upfront investment and ongoing infrastructure maintenance. 1 Furthermore, it provides better scalability, accessibility, and easier administration. The resources of the underlying host environment are usually virtualized, following a multitenant approach.That is, applications of different users may share the same virtual machines (VMs). 2 A service level agreement (SLA) is a contract between the SaaS cloud provider and the end-users. It defines the type of the provided service, the quality of service (QoS) requirements and the adopted pricing scheme. 3Applications in SaaS clouds usually have firm deadlines, within which they must finish execution. Such applications are typically referred to as real-time, as the correctness of their output does not only depend on the logical results of the computations but also on the time at which the results are produced. If a real-time application with a firm deadline cannot finish execution within its deadline, then its results will be useless. 4,5Based on the observation that it is often more...

show abstract

A Specification Framework for Real-Time Scheduling

Subramani

2002

SOFSEM 2002: Theory and Practice of Informatics

View full text Add to dashboard Cite

Algorithms for scheduling real-time tasks with input error and end-to-end deadlines

Cited by 47 publications

References 15 publications

Totally Clairvoyant Scheduling with Relative Timing Constraints

Totally Clairvoyant Scheduling with Relative Timing Constraints

Scheduling real‐time bag‐of‐tasks applications with approximate computations in SaaS clouds

A Specification Framework for Real-Time Scheduling

Contact Info

Product

Resources

About