2005년 대한 생화학·분자생물학회 하계학술대회를 다녀와서

We consider the problem of fair resource allocation in a system containing different resource types, where each user may have different demands for each resource. To address this problem, we propose Dominant Resource Fairness (DRF), a generalization of max-min fairness to multiple resource types. We show that DRF, unlike other possible policies, satisfies several highly desirable properties. First, DRF incentivizes users to share resources, by ensuring that no user is better off if resources are equally partitioned among them. Second, DRF is strategy-proof, as a user cannot increase her allocation by lying about her requirements. Third, DRF is envy-free, as no user would want to trade her allocation with that of another user. Finally, DRF allocations are Pareto efficient, as it is not possible to improve the allocation of a user without decreasing the allocation of another user. We have implemented DRF in the Mesos cluster resource manager, and show that it leads to better throughput and fairness than the slot-based fair sharing schemes in current cluster schedulers.

https://static.usenix.org/event/nsdi11/tech/full_papers/Ghodsi.pdf

Dominant resource fairness: fair allocation of multiple resource types

Premises of creation of Internet portal designed to provide access to participants of educational and scientific process for the joint creation, consolidation, concentration and rapid spreading of educational and scientific information resources in its own depository are considered. CMS-based portal content management systems’ potentiality is investigated. Architecture for Internet portal of MES of Ukraine’s information resources is offered.

Створення порталу інформаційно-довідкових ресурсів міністерства освіти і науки україни

This survey covers hard real-time scheduling algorithms and schedulability analysis techniques for homogeneous multiprocessor systems. It reviews the key results in this field from its origins in the late 1960s to the latest research published in late 2009. The survey outlines fundamental results about multiprocessor real-time scheduling that hold independent of the scheduling algorithms employed. It provides a taxonomy of the different scheduling methods, and considers the various performance metrics that can be used for comparison purposes. A detailed review is provided covering partitioned, global, and hybrid scheduling algorithms, approaches to resource sharing, and the latest results from empirical investigations. The survey identifies open issues, key research challenges, and likely productive research directions.

/pdf/a-survey-of-hard-real-time-scheduling-for-multiprocessor-313o35g6ho.pdf

A survey of hard real-time scheduling for multiprocessor systems

In this chapter, you will see how the simplex method simplifies when it is applied to a class of optimization problems that are known as “network flow models.” You will also see that if a network flow model has “integer-valued data,” the simplex method finds an optimal solution that is integer-valued.

Flows in Networks

A scheduling policy or a schedulability test is defined to be sustainable if any task system determined to be schedulable remains so if it behaves "better" than mandated by its system specifications. We provide a formal definition of sustainability, and subject the concept to systematic analysis in the context of the uniprocessor scheduling of periodic and sporadic task systems. We argue that it is, in general, preferable engineering practice to use sustainable tests if possible, and classify common uniprocessor schedulability tests according to whether they are sustainable or not.

/pdf/sustainability-in-real-time-scheduling-19pn0oi5r5.pdf

Sustainability in Real-time Scheduling

A federated approach to the multiprocessor scheduling of systems of independent recurrent tasks is considered, in which each task is either restricted to execute preemptively upon a single processor, or may execute upon multiple processors but gets exclusive access to all these processors. Efficient polynomial-time algorithms are derived here for the federated schedulability analysis and run-time scheduling of re-current task systems that are represented by the conditional sporadic DAG tasks model. The performance of these algorithms is characterized via a speedup factor metric, which quanti es the combined cost of both restricting oneself to the federated scheduling paradigm, and of requiring the scheduling algorithms to run in polynomial time.

The federated scheduling of systems of conditional sporadic DAG tasks

The constant bandwidth server (CBS) framework of L. Abeni and G. Buttazzo (1998) guarantees timely execution to individual threads in certain kinds of real time environments. An extension to the CBS framework is proposed, which permits the partitioning of the set of threads comprising the system into subsets representing individual applications, and extends timeliness guarantees to these applications as well.

A hierarchical extension to the constant bandwidth server framework

The priority-driven scheduling of periodic and sporadic task systems upon identical multiprocessor platforms is considered, under the restrictions that (i) each job may be assigned exactly one priority throughout its lifetime, and (ii) each job may execute upon only a single processor It is shown that the feasibility-analysis under these restrictions is intractable (NP-hard in the strong sense) A scheduling algorithm is presented that satisfies these restrictions, and that has a worst-case utilization bound comparable to the worst-case utilization bounds of partitioned scheduling algorithms, and of scheduling algorithms that retain the priority-assignment restriction but allow arbitrary interprocessor migration

Multiprocessor fixed-priority scheduling with restricted interprocessor migrations

Optimal online scheduling algorithms are known for sporadic task systems scheduled upon a single processor. Additionally, optimal online scheduling algorithms are also known for restricted subclasses of sporadic task systems upon an identical multiprocessor platform. The research reported in this article addresses the question of existence of optimal online multiprocessor scheduling algorithms for general sporadic task systems. Our main result is a proof of the impossibility of optimal online scheduling for sporadic task systems upon a system comprised of two or more processors. The result is shown by finding a sporadic task system that is feasible on a multiprocessor platform that cannot be correctly scheduled by any possible online, deterministic scheduling algorithm. Since the sporadic task model is a subclass of many more general real-time task models, the nonexistence of optimal scheduling algorithms for the sporadic task systems implies nonexistence for any model which generalizes the sporadic task model.

/pdf/optimal-online-multiprocessor-scheduling-of-sporadic-real-1f7x0fiq3a.pdf

Sanjoy Baruah

Papers

Sustainability in Real-time Scheduling

The federated scheduling of systems of conditional sporadic DAG tasks

A hierarchical extension to the constant bandwidth server framework

Multiprocessor fixed-priority scheduling with restricted interprocessor migrations

Optimal online multiprocessor scheduling of sporadic real-time tasks is impossible