Algorithms for end-to-end scheduling to meet deadlines

Bettati, Riccardo; Liu, J.W.S.

doi:10.1109/spdp.1990.143508

Cited by 18 publications

(18 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In [2], earliest-effective-deadline-first was shown to be an optimal non-preemptive scheduling policy for distributed systems, when the execution times of tasks are the same across all the stages of the distributed system. The delay composition rule derived in this paper can help in the search for an optimal scheduling policy for distributed systems with arbitrary task characteristics.…”

Section: Discussionmentioning

confidence: 99%

“…This is because the higher priority jobs can overtake J 1 in the DAG, which corresponds to the equivalent higher priority jobs preempting J * e in the uniprocessor system. By the delay composition theorem, the total delay incurred by J 1 in the acyclic distributed system under non-preemptive scheduling is no larger than the delay of J * e on the uniprocessor under preemptive scheduling, since the latter adds up to the delay bound expressed on the right hand of Inequality (2).…”

Section: Non-preemptive Scheduling Transformationmentioning

confidence: 99%

See 1 more Smart Citation

Transforming Distributed Acyclic Systems into Equivalent Uniprocessors under Preemptive and Non-Preemptive Scheduling

Jayachandran

Abdelzaher

2008

2008 Euromicro Conference on Real-Time Systems

View full text Add to dashboard Cite

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Non-preemptive Scheduling Transformationmentioning

confidence: 99%

Transforming Distributed Acyclic Systems into Equivalent Uniprocessors under Preemptive and Non-Preemptive Scheduling

Jayachandran

Abdelzaher

2008

2008 Euromicro Conference on Real-Time Systems

View full text Add to dashboard Cite

show abstract

“…We summarize these efforts and contrast them with our work. Bettati and Liu [22], [23] present an approach for scheduling preallocated flowshop (sequential) tasks in a hard realtime distributed environment. In their model, global tasks consist of (same) set of subtasks to be executed on nodes in the same order.…”

Section: Past Workmentioning

confidence: 99%

Time/Utility Function Decomposition in Soft Real-Time Distributed Systems

Jensen¹

2004

View full text Add to dashboard Cite

We consider RealTime CORBA 2.0 (Dynamic Scheduling) distributable threads, whose time constraints are specified using time/utility functions (TUFs), operating in legacy environments. In legacy environments, system node resources-both physical (processor, disk, I/O, etc.) and logical (locks, etc.)-are shared among timecritical distributable threads and local applications that may or may not be timecritical. Thus, in such environments, distributable threads that are scheduled using their propagated TUFs and scheduling parameters, as mandated by RealTime CORBA 2.0's Case 2 approach, may suffer performance degradation, if a node scheduler can achieve higher local accrued utility by giving higher eligibility to local threads than to distributable threads.To alleviate this, we consider decomposing TUFs of distributable threads into "subTUFs" that are used for scheduling segments of distributable threads. We present methods for decomposing TUFs. Furthermore, we identify conditions under which TUF decomposition can alleviate perfor mance degradation. Our experimental results reveal that the most important factors that affect the performance of TUF decomposition include the properties of node scheduling algorithms, TUF shapes, task load, Global Slack F actor, local threads and resource dependencies, and that these factors interact.

show abstract

“…Each node services their tasks according to some real-time scheduling algorithm with no preemption. In this paper, we use earliest-deadlinerst 4 as the scheduling algorithm for most of our experiments, mainly due to its popularity. W e will also discuss brie y the case when minimum-laxity-rst 5 is used as the scheduler algorithm in Section 7.…”

Section: Nodesmentioning

confidence: 99%

Deadline assignment in a distributed soft real-time system

Kao

García-Molina

1997

IEEE Trans. Parallel Distrib. Syst.

114

View full text Add to dashboard Cite

In a distributed environment, tasks often have processing demands on multiple di erent sites. A distributed task is usually divided up into several subtasks, each one to be executed at some site in order. In a real-time system, an overall deadline is usually speci ed by an application designer indicating when a distributed task is to be nished. However, the problem of how a global deadline is automatically translated to the deadline of each individual subtask has not been well studied. This paper examines through simulations four strategies for subtask deadline assignment in a distributed soft real-time environment.

show abstract

Algorithms for end-to-end scheduling to meet deadlines

Cited by 18 publications

References 8 publications

Transforming Distributed Acyclic Systems into Equivalent Uniprocessors under Preemptive and Non-Preemptive Scheduling

Transforming Distributed Acyclic Systems into Equivalent Uniprocessors under Preemptive and Non-Preemptive Scheduling

Time/Utility Function Decomposition in Soft Real-Time Distributed Systems

Deadline assignment in a distributed soft real-time system

Contact Info

Product

Resources

About