Results 1  10
of
37
A categorization of realtime multiprocessor scheduling problems and algorithms
 HANDBOOK ON SCHEDULING ALGORITHMS, METHODS, AND MODELS
, 2004
"... ..."
An optimal realtime scheduling algorithm for multiprocessors
 In Proc. 27th IEEE International RealTime Systems Symposium, Rio de Janeiro
, 2006
"... Abstract — We consider several object sharing synchronization mechanisms including lockbased, lockfree, and waitfree sharing for LNREF [1], an optimal realtime scheduling algorithm on multiprocessors. We derive LNREF’s minimumrequired space cost for waitfree synchronization using the spaceopt ..."
Abstract

Cited by 50 (0 self)
 Add to MetaCart
(Show Context)
Abstract — We consider several object sharing synchronization mechanisms including lockbased, lockfree, and waitfree sharing for LNREF [1], an optimal realtime scheduling algorithm on multiprocessors. We derive LNREF’s minimumrequired space cost for waitfree synchronization using the spaceoptimal waitfree algorithm. We then establish the feasibility conditions for lockfree and lockbased sharing under LNREF, and the concomitant tradeoffs. While the tradeoff between waitfree versus the other sharing is obvious, i.e., space and time costs, we show that the tradeoff between lockfree and lockbased sharing for LNREF hinges on the cost of the lockfree retry, blocking time under lockbased. Finally, we numerically evaluate lockfree and lockbased sharing for LNREF. I.
Efficient scheduling of soft realtime applications on multiprocessors
 In Proceedings of the 15th Euromicro Conference on Realtime Systems
, 2003
"... In soft realtime applications, tasks are allowed to miss their deadlines. Thus, lesscostly scheduling algorithms can be used at the price of occasional violations of timing constraints. This may be acceptable if reasonable tardiness bounds (i.e., bounds on the extent to which deadlines may be miss ..."
Abstract

Cited by 43 (20 self)
 Add to MetaCart
(Show Context)
In soft realtime applications, tasks are allowed to miss their deadlines. Thus, lesscostly scheduling algorithms can be used at the price of occasional violations of timing constraints. This may be acceptable if reasonable tardiness bounds (i.e., bounds on the extent to which deadlines may be missed) can be guaranteed. In this paper, we consider soft realtime applications implemented on multiprocessors. Pfair scheduling algorithms are the only known means of optimally scheduling hard realtime applications on multiprocessors. For this reason, we consider the use of such algorithms here. In the design of Pfair scheduling algorithms, devising schemes to correctly break ties when several tasks have the same deadline is a critical issue. Such tiebreaking schemes entail overhead that may be unacceptable or unnecessary in soft realtime applications. In this paper, we consider the earliest pseudodeadline first (EPDF) Pfair algorithm, which avoids this overhead by using no tiebreaking information. Our main contributions are twofold. First, we establish a condition for ensuring a tardiness of at most one quantum under EPDF. This condition is very liberal and should often hold in practice. Second, we present simulation results involving randomlygenerated task sets, including those that do not satisfy our condition. In these experiments, deadline misses rarely occurred, and no misses by more than one quantum ever occurred. ∗ Work supported by NSF grants CCR 9972211, CCR 9988327, ITR 0082866, and CCR 0204312. 1
A comparison of global and partitioned EDF schedulability tests for multiprocessors
 In International Conf. on RealTime and Network Systems
, 2005
"... This paper compares the performance of several variations on EDFbased global and partitioned multiprocessor scheduling algorithms, together with their associated feasibility tests, on a variety of pseudorandomly chosen sets of sporadic tasks. A new hybrid EDFbased scheme is shown to perform bette ..."
Abstract

Cited by 42 (1 self)
 Add to MetaCart
(Show Context)
This paper compares the performance of several variations on EDFbased global and partitioned multiprocessor scheduling algorithms, together with their associated feasibility tests, on a variety of pseudorandomly chosen sets of sporadic tasks. A new hybrid EDFbased scheme is shown to perform better than previously studied prioritybased global scheduling schemes, though not as well as EDFbased firstfit partitioned scheduling. 1
On the Implementation of Pfairscheduled Multiprocessor Systems
, 2004
"... The goal of this dissertation is to extend the Pfair scheduling approach in order to enable its efficient implementation on a realtime multiprocessor. At present, Pfair scheduling is the only known means for optimally scheduling recurrent realtime tasks on multiprocessors. In
addition, there has b ..."
Abstract

Cited by 30 (12 self)
 Add to MetaCart
The goal of this dissertation is to extend the Pfair scheduling approach in order to enable its efficient implementation on a realtime multiprocessor. At present, Pfair scheduling is the only known means for optimally scheduling recurrent realtime tasks on multiprocessors. In
addition, there has been growing practical interest in such approaches due to their fairness
guarantees. Unfortunately, prior work in this area has considered only the scheduling of
independent tasks, which do not communicate with each other or share resources. The work
presented herein focuses both on adding support for these actions and also on developing
techniques for reducing various forms of implementation overhead, including that produced
by task migrations and context switches. The thesis of this dissertation is:
tasks can be efficiently synchronized in Pfairscheduled systems and overhead due
to common system events, such as context switches and migrations, can be reduced.
This thesis is established through research in three areas. First, the preexisting Pfair schedul
ing theory is extended to support the scheduling of groups of tasks as a single entity. Second,
mechanisms for supporting both lockbased and lockfree synchronization are presented. Lock
based synchronization coordinates access to shared resources through the use of semaphores.
On the other hand, lockfree operations are optimistically attempted and then retried if the
operation fails. Last, the deployment of Pfair scheduling on a symmetric multiprocessor is
considered.
Efficient realtime scheduling algorithms for multiprocessor systems
 IEICE Trans. Communications
, 2002
"... We present an optimal realtime scheduling algorithm for multiprocessors — one that satisfies all task deadlines, when the total utilization demand does not exceed the utilization capacity of the processors. The algorithm called LLREF, is designed based on a novel abstraction for reasoning about tas ..."
Abstract

Cited by 28 (0 self)
 Add to MetaCart
(Show Context)
We present an optimal realtime scheduling algorithm for multiprocessors — one that satisfies all task deadlines, when the total utilization demand does not exceed the utilization capacity of the processors. The algorithm called LLREF, is designed based on a novel abstraction for reasoning about task execution behavior on multiprocessors: the Time and Local Execution Time Domain Plane (or TL plane). LLREF is based on the fluid scheduling model and the fairness notion, and uses the TL plane to describe fluid schedules without using time quanta, unlike the optimal Pfair algorithm (which uses time quanta). We show that scheduling for multiprocessors can be viewed as repeatedly occurring TL planes, and feasibly scheduling on a single TL plane results in the optimal schedule. We analytically establish the optimality of LLREF. Further, we establish that the algorithm has bounded overhead, and this bound is independent of time quanta (unlike Pfair). Our simulation results validate our analysis on the algorithm overhead.
Schedulability analysis of multiprocessor sporadic task systems
 Handbook of Realtime and Embedded Systems
, 2007
"... ..."
(Show Context)
Efficient and Flexible Fair Scheduling of Realtime Tasks on Multiprocessors
 University
, 2003
"... ..."
(Show Context)
Comparison of empirical success rates of global vs. partitioned fixedpriority and EDF scheduling for hard real time
, 2005
"... Improvements in schedulability tests for global fixedpriority and EDF scheduling in a homogeneous multiprocessor (symmetric multiprocessing) environment have shown that the worstcase guaranteed achievable utilization levels for global EDF scheduling equals what can be achieved with partitioned sch ..."
Abstract

Cited by 22 (1 self)
 Add to MetaCart
(Show Context)
Improvements in schedulability tests for global fixedpriority and EDF scheduling in a homogeneous multiprocessor (symmetric multiprocessing) environment have shown that the worstcase guaranteed achievable utilization levels for global EDF scheduling equals what can be achieved with partitioned scheduling, and both ways of applying EDF scheduling outperform fixedpriority scheduling, for sets of independent periodic or sporadic harddeadline tasks with deadline equal to period. However, less is known about the comparative performance of the partitioned vs. global and EDF vs. fixedpriority approaches in the average and without the restriction that deadline equal period, and particular which of the known combinations of a scheduling algorithm and a sufficient a priori test of schedulability is more likely to succeed in verifiably scheduling a set of tasks to meet all deadlines. This paper compares the performance of several such combinations on a variety of pseudorandomly chosen sets of sporadic tasks. 1
Dpfair: A simple model for understanding optimal multiprocessor scheduling
 In Proc. of the 2010 22nd Euromicro Conf. on RealTime Sys
, 2010
"... We consider the problem of optimal realtime scheduling of periodic and sporadic tasks for identical multiprocessors. A number of recent papers have used the notions of fluid scheduling and deadline partitioning to guarantee optimality and improve performance. In this paper, we develop a unifying th ..."
Abstract

Cited by 11 (0 self)
 Add to MetaCart
(Show Context)
We consider the problem of optimal realtime scheduling of periodic and sporadic tasks for identical multiprocessors. A number of recent papers have used the notions of fluid scheduling and deadline partitioning to guarantee optimality and improve performance. In this paper, we develop a unifying theory with the DPFAIR scheduling policy and examine how it overcomes problems faced by greedy scheduling algorithms. We then present a simple DPFAIR scheduling algorithm, DPWRAP, which serves as a least common ancestor to many recent algorithms. We also show how to extend DPFAIR to the scheduling of sporadic tasks with arbitrary deadlines. 1.