Results 1  10
of
318
Dominant resource fairness: Fair allocation of multiple resource types
, 2011
"... 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 maxmin fairness to multiple resource types. We ..."
Abstract

Cited by 146 (15 self)
 Add to MetaCart
(Show Context)
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 maxmin 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 strategyproof, as a user cannot increase her allocation by lying about her requirements. Third, DRF is envyfree, 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 slotbased fair sharing schemes in current cluster schedulers. 1
Fast Scheduling of Periodic Tasks on Multiple Resources
 In Proceedings of the 9th International Parallel Processing Symposium
"... Given n periodic tasks, each characterized by an execution requirement and a period, and m identical copies of a resource, the periodic scheduling problem is concerned with generating a schedule for the n tasks on the m resources. We present an algorithm that schedules every feasible instance of t ..."
Abstract

Cited by 129 (15 self)
 Add to MetaCart
Given n periodic tasks, each characterized by an execution requirement and a period, and m identical copies of a resource, the periodic scheduling problem is concerned with generating a schedule for the n tasks on the m resources. We present an algorithm that schedules every feasible instance of the periodic scheduling problem, and runs in O(minfm lg n; ng) time per slot scheduled. 1 Introduction Given a set \Gamma of n tasks, where each task x is characterized by two integer parameters x:e and x:p, and m identical copies of a resource, a periodic schedule is one that allocates a resource to each task x in \Gamma for exactly x:e time units in each interval [k \Delta x:p; (k+1) \Delta x:p) for all k in N, subject to the following constraints: Constraint 1: A resource can only be allocated to a task for an entire "slot" of time, where for each i in N slot i is the unit interval from time i to time i + 1. Constraint 2: No task may be allocated more than one copy of the resource ...
PriorityDriven Scheduling of Periodic Task Systems on Multiprocessors
, 2001
"... The scheduling of systems of periodic tasks upon multiprocessor platforms is considered. ..."
Abstract

Cited by 122 (16 self)
 Add to MetaCart
The scheduling of systems of periodic tasks upon multiprocessor platforms is considered.
Scheduling with dynamic voltage/speed adjustment using slack reclamation in multiprocessor realtime systems
 IEEE TRANS. ON PARALLEL AND DISTRIBUTED SYSTEMS
, 2003
"... The high power consumption of modern processors becomes a major concern because it leads to decreased mission duration (for batteryoperated systems), increased heat dissipation, and decreased reliability. While many techniques have been proposed to reduce power consumption for uniprocessor systems ..."
Abstract

Cited by 116 (10 self)
 Add to MetaCart
(Show Context)
The high power consumption of modern processors becomes a major concern because it leads to decreased mission duration (for batteryoperated systems), increased heat dissipation, and decreased reliability. While many techniques have been proposed to reduce power consumption for uniprocessor systems, there has been considerably less work on multiprocessor systems. In this paper, based on the concept of slack sharing among processors, we propose two novel poweraware scheduling algorithms for task sets with and without precedence constraints executing on multiprocessor systems. These scheduling techniques reclaim the time unused by a task to reduce the execution speed of future tasks and, thus, reduce the total energy consumption of the system. We also study the effect of discrete voltage/speed levels on the energy savings for multiprocessor systems and propose a new scheme of slack reservation to incorporate voltage/speed adjustment overhead in the scheduling algorithms. Simulation and tracebased results indicate that our algorithms achieve substantial energy savings on systems with variable voltage processors. Moreover, processors with a few discrete voltage/speed levels obtain nearly the same energy savings as processors with continuous voltage/speed, and the effect of voltage/speed adjustment overhead on the energy savings is relatively small.
Mixed Pfair/ERfair Scheduling of Asynchronous Periodic Tasks
, 2001
"... Pfair Scheduling was proposed by... In this paper, we introduce a workconserving variant of Pfair scheduling called "earlyrelease" fair (ERfair) scheduling. We also present a new scheduling algorithm called PD² and show that it is optimal for scheduling any mix of earlyrelease ..."
Abstract

Cited by 113 (46 self)
 Add to MetaCart
(Show Context)
Pfair Scheduling was proposed by... In this paper, we introduce a workconserving variant of Pfair scheduling called "earlyrelease" fair (ERfair) scheduling. We also present a new scheduling algorithm called PD&sup2; and show that it is optimal for scheduling any mix of earlyrelease and nonearlyrelease asynchronous, periodic tasks. In contrast, almost all prior work on Pfair scheduling has been limited to synchronous systems. PD&sup2;is an optimization of an earlier deadlinebased algorithm of Baruah, Gehrke, and Plaxton called PD; PD&sup2; uses a simpler tiebreaking scheme than PD to disambiguate equal deadlines. We present a series of counterexamples that suggest that, in general, the PD&sup2; tiebreaking mechanism cannot be simplified. In contrast to this, we show that no tiebreaking information is needed on twoprocessor systems.
A categorization of realtime multiprocessor scheduling problems and algorithms
 HANDBOOK ON SCHEDULING ALGORITHMS, METHODS, AND MODELS
, 2004
"... ..."
Resource partitioning among realtime applications
 IN PROCEEDINGS OF EUROMICRO CONFERENCE ON REALTIME SYSTEMS
, 2003
"... When executing different realtime applications on a single processor system, one problem is how to compose these applications and guarantee at the same time that their timing requirements are not violated. A possible way of composing applications is through the resource reservation approach. Each a ..."
Abstract

Cited by 104 (17 self)
 Add to MetaCart
When executing different realtime applications on a single processor system, one problem is how to compose these applications and guarantee at the same time that their timing requirements are not violated. A possible way of composing applications is through the resource reservation approach. Each application is handled by a dedicated server that is assigned a fraction of the processor. Using this approach, the system can be seen as a twolevel hierarchical scheduler. A considerable amount of work has been recently addressed to the analysis of this kind of hierarchical systems. However, a question is still unanswered: given a set of realtime tasks to be handled by a server, how to assign the server parameters so that the task set is feasible? In this paper, we answer to the previous question for the case of fixed priority local scheduler by presenting a methodology for computing the class of server parameters that make the task set feasible.
A survey of hard realtime scheduling for multiprocessor systems
 ACM COMPUTING SURVEYS
, 2011
"... This survey covers hard realtime 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 ab ..."
Abstract

Cited by 99 (9 self)
 Add to MetaCart
This survey covers hard realtime 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 realtime 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.
Quickrelease Fair Scheduling
 In Proceedings of the 12th Euromicro Conference on RealTime Systems
, 2003
"... In prior work on multiprocessor fairness, efficient techniques with provable properties for reallocating spare processing capacity have been elusive. In this paper, we address this shortcoming by proposing a new notion of multiprocessor fairness, called quickrelease fair (QRfair) scheduling, which ..."
Abstract

Cited by 97 (36 self)
 Add to MetaCart
In prior work on multiprocessor fairness, efficient techniques with provable properties for reallocating spare processing capacity have been elusive. In this paper, we address this shortcoming by proposing a new notion of multiprocessor fairness, called quickrelease fair (QRfair) scheduling, which is a derivative of Pfair scheduling that allows efficient allocation of spare capacity. Under QRfair scheduling, each task is specified by giving both a minimum and a maximum weight (i.e., processor share). The goal is to schedule each task (as the available spare capacity changes) at a rate that is (i) at least that implied by its minimum weight and (ii) at most that implied by its maximum weight. Our contributions are fourfold. First, we present a quickrelease variant of the PD Pfair scheduling algorithm called PD . Second, we formally prove that the allocations of PD always satisfy (i) and (ii). Third, we consider the problem of defining maximum weights in a way that encourages a fair distribution of spare capacity. Fourth, we present results from extensive simulation experiments that show the efficacy of PD in allocating spare capacity.
Optimal Ratebased Scheduling on Multiprocessors
 In Proceedings of the 34th ACM Symposium on Theory of Computing
, 2001
"... We consider the intrasporadic task model, which is a generalization of the sporadic task model motivated by recent work on Pfair scheduling. The intrasporadic model is essentially a quantumbased, multiprocessor variant of the uniprocessor ratebased execution model of Jeffay and Goddard. In the i ..."
Abstract

Cited by 81 (41 self)
 Add to MetaCart
(Show Context)
We consider the intrasporadic task model, which is a generalization of the sporadic task model motivated by recent work on Pfair scheduling. The intrasporadic model is essentially a quantumbased, multiprocessor variant of the uniprocessor ratebased execution model of Jeffay and Goddard. In the intrasporadic model, a task is specified by an average rate of execution, and there is no restriction on instantaneous execution rates. Such exibility is useful in applications in which some processing steps may be highly jittered. In previous work, we showed that an intrasporadic task system is feasible on M processors i its total utilization is at most M . We also gave an optimal algorithm for scheduling intrasporadic tasks on two processors. In this paper, we show that the PD&sup2; Pfair algorithm can be used to schedule any intrasporadic task system that is feasible on M processors. Because the sporadic model is a special case of the intrasporadic model, our work shows that PD&sup2; is also optimal for scheduling sporadic tasks on a multiprocessor. This paper is the first to show that sporadic or intrasporadic tasks can be optimally scheduled on systems of more than two processors.