Showing papers on "Deadline-monotonic scheduling published in 2002"

Project Scheduling: A Research Handbook

Abstract: Scope and Relevance of Project Scheduling.- The Project Scheduling Process.- Classification of Project Scheduling Problems.- Temporal Analysis: The Basic Deterministic Case.- Temporal Analysis: Advanced Topics.- The Resource-Constrained Project Scheduling Problem.- Resource-Constrained Scheduling: Advanced Topics.- Project Scheduling with Multiple Activity Execution Modes.- Stochastic Project Scheduling.- Robust and Reactive Scheduling.

Multicriteria Scheduling: Theory, Models and Algorithms

Abstract: Scheduling and multicriteria optimisation theory have been subject, separately, to numerous studies. Since the last twenty years, multicriteria scheduling problems have been subject to a growing interest. However, a gap between multicriteria scheduling approaches and multicriteria optimisation field exits. This book is an attempt to collect the elementary of multicriteria optimisation theory and the basic models and algorithms of multicriteria scheduling. It is composed of numerous illustrations, algorithms and examples which may help the reader in understanding the presented concepts. This book covers general concepts such as Pareto optimality, complexity theory, and general method for multicriteria optimisation, as well as dedicated scheduling problems and algorithms: just-in-time scheduling, flexibility and robustness, single machine problems, parallel machine problems, shop problems, etc. The second edition contains revisions and new material.

Project Scheduling with Time Windows and Scarce Resources

Abstract: 1 Temporal Project Scheduling.- 1.1 Minimum and maximum time lags.- 1.2 Activity-on-node project networks.- 1.3 Temporal project scheduling computations.- 1.4 Orders in the set of activities.- 2 Resource-Constrained Project Scheduling - Minimization of Project Duration.- 2.1 Formulation of the problem.- 2.2 Cycle structures in activity-on-node project networks.- 2.3 Properties of the feasible region.- 2.3.1 Strict orders and order polyhedra.- 2.3.2 Forbidden sets and resolution of resource conflicts.- 2.4 Different types of shifts and sets of schedules.- 2.5 Branch-and-bound and truncated branch-and-bound methods.- 2.5.1 Enumeration scheme.- 2.5.2 Preprocessing.- 2.5.3 Lower bounds.- 2.5.4 Branch-and-bound algorithm.- 2.5.5 Truncated branch-and-bound methods.- 2.5.6 Alternative enumeration schemes.- 2.5.7 Alternative preprocessing and constraint propagation.- 2.5.8 Alternative lower bounds.- 2.6 Priority-rule methods.- 2.6.1 Direct method.- 2.6.2 Decomposition methods.- 2.6.3 Priority rules.- 2.6.4 Serial generation scheme.- 2.6.5 Parallel generation scheme.- 2.7 Schedule-improvement procedures.- 2.7.1 Genetic algorithm.- 2.7.2 Tabu search.- 2.8 Experimental performance analysis.- 2.8.1 Random generation of projects.- 2.8.2 Computational experience.- 2.9 Application to make-to-order production in manufacturing industry.- 2.10 Regular objective functions different from project duration.- 2.11 Calendarization.- 2.12 Project scheduling with cumulative resources.- 2.12.1 Discrete cumulative resources.- 2.12.2 Continuous cumulative resources.- 2.13 Project scheduling with synchronizing resources.- 2.14 Project scheduling with sequence-dependent changeover times.- 2.15 Multi-mode project scheduling problems.- 2.15.1 Problem formulation and basic properties.- 2.15.2 Solution methods.- 2.16 Application to batch production in process industries.- 2.16.1 Case study.- 2.16.2 Batching problem.- 2.16.3 Project scheduling model for batch scheduling.- 2.16.4 Solution procedure for batch scheduling.- 3 Resource-Constrained Project Scheduling - Minimization of General Objective Functions.- 3.1 Different objective functions.- 3.2 Additional types of shifts and sets of schedules.- 3.3 Classification of objective functions.- 3.3.1 Separable and resource-utilization dependent objective functions.- 3.3.2 Class 1 of regular objective functions.- 3.3.3 Class 2 of antiregular objective functions.- 3.3.4 Class 3 of convex objective functions.- 3.3.5 Class 4 of binary-monotone objective functions.- 3.3.6 Class 5 of quasiconcave objective functions.- 3.3.7 Class 6 of locally regular objective functions.- 3.3.8 Class 7 of locally quasiconcave objective functions.- 3.4 Time complexity of time-constrained project scheduling.- 3.5 Relaxation-based approach for function classes 1 to 5.- 3.5.1 General enumeration scheme.- 3.5.2 Branch-and-bound algorithm for the net present value problem.- 3.5.3 Branch-and-bound algorithm for the earliness-tardiness problem.- 3.6 Tree-based approach for function classes 6 and 7.- 3.6.1 General enumeration scheme.- 3.6.2 Branch-and-bound algorithms for resource investment, resource levelling, and resource renting problems.- 3.6.3 Experimental performance analysis.- 3.6.4 Alternative lower bounds.- 3.7 Priority-rule methods.- 3.7.1 Time-constrained project scheduling.- 3.7.2 Resource-constrained project scheduling.- 3.7.3 Experimental performance analysis.- 3.8 Schedule-improvement procedures.- 3.8.1 Neighborhoods for project scheduling problems.- 3.8.2 A tabu search procedure.- 3.9 Application to investment projects.- 3.9.1 Computation of the net present value function.- 3.9.2 Decision support.- 3.10 Hierarchical project planning.- References.- List of Symbols.- Three-Field Classification for Resource-Constrained Project Scheduling.

Symbiotic jobscheduling with priorities for a simultaneous multithreading processor

Abstract: Simultaneous Multithreading machines benefit from jobscheduling software that monitors how well coscheduled jobs share CPU resources, and coschedules jobs that interact well to make more efficient use of those resources. As a result, informed coscheduling can yield significant performance gains over naive schedulers. However, prior work on coscheduling focused on equal-priority job mixes, which is an unrealistic assumption for modern operating systems.This paper demonstrates that a scheduler for an SMT machine can both satisfy process priorities and symbiotically schedule low and high priority threads to increase system throughput. Naive priority schedulers dedicate the machine to high priority jobs to meet priority goals, and as a result decrease opportunities for increased performance from multithreading and coscheduling. More informed schedulers, however, can dynamically monitor the progress and resource utilization of jobs on the machine, and dynamically adjust the degree of multithreading to improve performance while still meeting priority goals.Using detailed simulation of an SMT architecture, we introduce and evaluate a series of five software and hardware-assisted priority schedulers. Overall, our results indicate that coscheduling priority jobs can significantly increase system throughput by as much as 40%, and that (1) the benefit depends upon the relative priority of the coscheduled jobs, and (2) more sophisticated schedulers are more effective when the differences in priorities are greatest. We show that our priority schedulers can decrease average turnaround times for a random jobmix by as much as 33%.

Scheduling in Real-Time Systems

Abstract: Introduction. 1. Basic Concepts. Real--time applications. Basic notions for real--time task scheduling. 2. Scheduling of Independent Tasks. Basic on--line algorithms for periodic tasks. Hybrid task sets scheduling. 3. Scheduling of Dependent Tasks. Tasks for precedence relationships. Tasks sharing critical resources. 4. Scheduling Schemes for Handling Overload. Scheduling techniques in overload conditions. Handling real--time tasks with varying timing parameters. Handling overload conditions for hybrid task sets. 5. Multiprocessor Scheduling. Introduction. First results and comparison with uniprocessor scheduling. Multiprocessor scheduling anomalies. Schedulability conditions. Scheduling algorithms. 6. Joint Scheduling of Tasks and Messages in Distributed Systems. Overview of distributed real--time systems. Task allocation in real--time distributed systems. Real--time traffic. Message scheduling. Conclusion. 7. Packet Scheduling in Networks. Introduction. Network and traffic models. Service disciplines. Work--conserving service disciplines. Non--work--conserving service disciplines. 8. Software Environment. Real--time operating system and real--time kernel. Real--time languages. Real--time middleware. Summary of scheduling capabilities of standardized components. 9. Case Studies. Real--time acquisition and analysis of rolling mill signals. Embedded real--time application: Mars Pathfinder mission. Distributed automotive application.

Scheduling Multiprocessor Tasks with Genetic Algorithms

Abstract: In this paper, an efficient method based on genetic algorithms is developed to solve the multiprocessor scheduling problem. To efficiently execute programs in parallel on multiprocessor scheduling problem must be solved to determine the assignment of tasks to the processors and the execution order of the tasks so that the execution time is minimized. Even when the target processors is fully connected and no communication delay is considered among tasks in the task graph the scheduling problem is NP-complete. Complexity of scheduling problems dependent of number of processors (P), task processing time Ti and precedence constraints. This problem has been known as strong NP-hard intractable optimisation problem when it assumes arbitrary number of processors, arbitrary task processing time and arbitrary precedence constraints. We assumed fixed number of processors and tasks are represented by a directed acyclic graph (DAG) called “task graph”.

Distributed priority scheduling and medium access in ad hoc networks

Abstract: Providing Quality-of-Service in random access multi-hop wireless networks requires support from both medium access and packet scheduling algorithms. However, due to the distributed nature of ad hoc networks, nodes may not be able to determine the next packet that would be transmitted in a (hypothetical) centralized and ideal dynamic priority scheduler. In this paper, we develop two mechanisms for QoS communication in multi-hop wireless networks. First, we devise distributed priority scheduling, a technique that piggybacks the priority tag of a node's head-of-line packet onto handshake and data packets; e.g., RTS/DATA packets in IEEE 802.11. By monitoring transmitted packets, each node maintains a scheduling table which is used to assess the node's priority level relative to other nodes. We then incorporate this scheduling table into existing IEEE 802.11 priority backoff schemes to approximate the idealized schedule. Second, we observe that congestion, link errors, and the random nature of medium access prohibit an exact realization of the ideal schedule. Consequently, we devise a scheduling scheme termed multi-hop coordination so that downstream nodes can increase a packet's relative priority to make up for excessive delays incurred upstream. We next develop a simple analytical model to quantitatively explore these two mechanisms. In the former case, we study the impact of the probability of overhearing another packet's priority index on the scheme's ability to achieve the ideal schedule. In the latter case, we explore the role of multi-hop coordination in increasing the probability that a packet satisfies its end-to-end QoS target. Finally, we perform a set of ns-2 simulations to study the scheme's performance under more realistic conditions.

Convergent scheduling

Abstract: Convergent scheduling is a general framework for cluster assignment and instruction scheduling on spatial architectures. A convergent scheduler is composed of independent passes, each implementing a heuristic that addresses a particular problem or constraint. The passes share a simple, common interface that provides spatial and temporal preference for each instruction. Preferences are not absolute; instead, the interface allows a pass to express the confidence of its preferences, as well as preferences for multiple space and time slots. A pass operates by modifying these preferences. By applying a series of passes that address all the relevant constraints, the convergent scheduler can produce a schedule that satisfies all the important constraints. Because all passes are independent and need to understand only one interface to interact with each other, convergent scheduling simplifies the problem of handling multiple constraints and co-developing different heuristics. We have applied convergent scheduling to two spatial architectures: the Raw processor and a clustered VLIW machine. It is able to successfully handle traditional constraints such as parallelism, load balancing, and communication minimization, as well as constraints due to preplaced instructions, which are instructions with predetermined cluster assignment. Convergent scheduling is able to obtain an average performance improvement of 21% over the existing space-time scheduler of the Raw processor, and an improvement of 14% over state-of-the-art assignment and scheduling techniques on a clustered VLIW architecture.

Optimal due date assignment in project scheduling

Abstract: In this paper we introduce the concept of due date assignment in the project scheduling literature. Despite the fact that due date assignment problems belongs to the core of the machine scheduling literature, no attempts have been made to tackle this problem in a project scheduling environment. However, of obvious practical importance, an optimal assignment of due dates is of primary interest to the project manager. In a recent research paper on project scheduling with due dates, the problem has been restricted to considering projects with pre-assigned due dates. In reality, due dates are the results of negotiations, rather than simply dictated by the client of the project. In this paper we consider this negotiation process and take a contractor's point of view who faces the problem of assigning due dates to a particular project, based on the negotiation arguments of the client. We show that the problem under study can be solved by means of the combination of different ideas from the operations research community.

Low-cost task scheduling for distributed-memory machines

Abstract: In compile-time task scheduling for distributed-memory systems, list scheduling is generally accepted as an attractive approach, since it pairs low cost with good results. List-scheduling algorithms schedule tasks in order of their priority. This priority can be computed either (1) statically, before the scheduling, or (2) dynamically, during the scheduling. In this paper, we show that list scheduling with statically-computed priorities (LSSP) can be performed at a significantly lower cost than existing approaches, without sacrificing performance. Our approach is general, i.e. it can be applied to any LSSP algorithm. The low complexity is achieved by using low-complexity methods for the most time-consuming parts in list-scheduling algorithms, i.e. processor selection and task selection, preserving the criteria used in the original algorithms. We exemplify our method by applying it to the MCP (Modified Critical Path) algorithm. Using an extension of this method, we can also reduce the time complexity of a particular class of list scheduling with dynamic priorities (LSDP) [including algorithms such as DLS (Dynamic Level Scheduling), ETF (Earliest Task First) and ERT (Earliest Ready Task)]. Our results confirm that the modified versions of the list-scheduling algorithms obtain a performance comparable to their original versions, yet at a significantly lower cost. We also show that the modified versions of the list-scheduling algorithms consistently outperform multi-step algorithms, such as DSC-LLB (Dynamic Sequence Clustering with List Load Balancing), which also have higher complexity and clearly outperform algorithms in the same class of complexity, such as CPM (Critical Path Method).

Exact best-case response time analysis of fixed priority scheduled tasks

Abstract: We present a solution for exact calculation of the best-case response times of a periodic task set with fixed priorities. The solution is based on the identification of the best-case phasing of a low priority task compared to the higher priority tasks. This phasing occurs when the low priority task is released such that it finishes simultaneously with the releases of all the higher priority tasks, when these have experienced their maximum release jitter. A recurrence equation is applied to find the best-case response time. The dualism between worst-case and best-case response time calculation is characterized. The most important application of the solution is in the analysis of response jitter.

Optimal rate-based scheduling on multiprocessors

Abstract: The PD2 Pfair/ERfair scheduling algorithm is the most efficient known algorithm for optimally scheduling periodic tasks on multiprocessors. In this paper, we prove that PD2 is also optimal for scheduling "rate-based" tasks whose processing steps may be highly jittered. The rate-based task model we consider generalizes the widely-studied sporadic task model.

An optimal scheduling algorithm based on task duplication

Abstract: Under the condition that the communication time is relatively shorter than the computation time for a given task, the task duplication-based scheduling (TDS) algorithm proposed by S. Darbha and D.P. Agrawal (1998) generates an optimal schedule. In this paper, we propose an extended TDS algorithm whose optimality condition is less restricted and where the length of the generated schedule is shorter than the original TDS algorithm.

Resource reservation for large-scale job scheduling

Abstract: A method is provided for scheduling software task execution. According to the method, at least one high priority software task that has a specified start time and at least one lower priority software task are accepted. There is determined a time remaining until the specified start time for the high priority software task, and there is determined if the lower priority software task can complete execution within the time remaining that was determined. The lower priority software task is executed only if it was determined to be able to complete execution within the time remaining, and the high priority software task is executed at or very near the specified start time. In a preferred embodiment, all incoming software tasks are placed on a task queue with a status of hold to prevent execution.

Method of setting priority levels in a multiprogramming computer system with priority scheduling, multiprogramming computer system and program therefor

Abstract: A method for setting priority levels in a multiprogramming computer system (1) with priority scheduling, in which threads (15, 16, 17) of execution of each process (13, 14) have a standard priority level, comprises measuring relative use of one or more processors (2) in the system (1) by the threads (15, 16, 17) of execution of a process (13, 14). The priority levels of one or more threads (15, 16, 17) of execution are lowered if their measured relative use exceeds a certain escalation threshold for the duration of an escalation time period (.DELTA.T1.

A realistic model and an efficient heuristic for scheduling with heterogeneous processors

Abstract: Scheduling computational tasks on processors is a key issue for high-performance computing. Although a large number of scheduling heuristics have been presented in the literature, most of them target only homogeneous resources. Moreover, these heuristics often rely on a model where the number of processors is bounded but where the communication capabilities of the target architecture are not restricted. In this paper, we deal with a more realistic model for heterogeneous networks of workstations, where each processor can send and/or receive at most one message at any given time-step. First, we state a complexity result that shows that the model is at least as difficult as the standard one. Then, we show how to modify classical list scheduling techniques to cope with the new model. Next we introduce a new scheduling heuristic which incorporates load-balancing criteria into the decision process of scheduling and mapping ready tasks. Experimental results conducted using six classical testbeds (LAPLACE, LU, STENCIL, FORK-JOIN, DOOLITTLE, and LDMt) show very promising results.

Method and apparatus for scheduling a resource to meet quality-of-service restrictions

Abstract: The present invention is directed to a method and apparatus for scheduling a resource (35) to meet quality of service guarantees. In one embodiment of three levels of priority, if a channel of a first priority level (15) is within its bandwidth allocation, then a request is issued from that channel. If there are no requests in channels at the first priority level that are within the allocation, requests from channels at the second priority level (20) that are within their bandwidth allocation are chosen. If there are no requests of this type, requests from channels at the third priority level (25) or requests from channels at the first and second levels that are outside of their bandwidth allocation are issued. The system may be implemented using rate-based scheduling.

Effective Selection of Partition Sizes for Moldable Scheduling of Parallel Jobs

Abstract: Although the current practice in parallel job scheduling requires jobs to specify a particular number of requested processors, most parallel jobs are moldable, i.e. the required number of processors is flexible. This paper addresses the issue of effective selection of processor partition size for moldable jobs. The proposed scheduling strategy is shown to provide significant benefits over a rigid scheduling model and is also considerably better than a previously proposed approach to moldable job scheduling.

Method and system for routing mobile vehicles and scheduling maintenance for those vehicles related application

Abstract: Methods and systems for routing and scheduling maintenance for aircraft. An aircraft routing and maintenance scheduling system generates an aircraft routing proposal based on information describing a possible flight of an aircraft and a maintenance scheduling proposal that corresponds to the aircraft based on information describing a possible maintenance schedule of the aircraft. The system determines a proposed flight assignment and proposed maintenance scheduling assignment based on the aircraft routing proposal and maintenance scheduling proposal. Thereafter, the system produces a flight assignment plan and maintenance scheduling plan using the proposed flight assignment and proposed maintenance scheduling assignment when the proposed flight assignment and proposed maintenance scheduling assignment meet a decision criterion describing requirements for aircraft routing and maintenance scheduling.

Scheduling Independent Tasks with QoS Requirements in Grid Computing with Time-Varying Resource Prices

Abstract: This paper considers the problem of scheduling a set of independent tasks with multiple QoS requirements, which may include timeliness, reliability, security, version, and priority, in a Grid computing system in which resource prices can vary with time during scheduling time intervals. This problem is referred to as the QoS-based scheduling problem with time-varying resource prices. In order to solve this problem, a static scheduling algorithm (QSMTS VP) is developed. The simulation studies carried out show that QSMTS VP is capable of meeting diverse QoS requirements of many users simultaneously and that QSMTS VP can react to the dynamics of the market. Thus, QSMTS VP is a promising heuristic that can be deployed in a computational market.

Analyzing fixed-priority global multiprocessor scheduling

Abstract: We consider a multiprocessor where hard real-time tasks are scheduled globally on in processors. Each task has a fixed priority and tasks are executed using preemptive scheduling. The state-of-the-art priority assignment scheme in such cases is called RM-US[US-LIMIT], where US-LIMIT is a parameter to the RM-US algorithm. The challenge is to find the US-LIMIT that can guarantee schedulability for as high utilization as possible. The previously best known US-LIMIT value could guarantee schedulability as long as the multiprocessor utilization is below m/(3m-2), i.e. 0.33333 when m/spl rarr//spl infin/. In this paper we define a new equation for US-LIMIT which guarantees schedulability for higher utilization values than the previous result. When m/spl rarr//spl infin/ we can now guarantee schedulability, for all tasks sets when the multiprocessor utilization is below 0.37482. We also show that our US-LIMIT values are optimal, i.e. we show that there is no room for further improvement of this state-of-the-art priority assignment scheme.

Programmable scheduling for ip routers

Abstract: A scheduling system for IP routers is provided. A programmable scheduler for IP routers can support single stage and multistage scheduling. This allows flexible combinations of scheduling and widens dramatically the available QoS (Quality of Service) solutions to operators. With this kind of scheduling the router through a scheduling configuration interface (355) to support almost any known scheduling method or combination. Priority Queuing (PQ) and Deficit Round Robin (DRR) methods are used according to one embodiment.

Selective preemption strategies for parallel job scheduling

Abstract: Although theoretical results have been established regarding the utility of pre-emptive scheduling in reducing average job turn-around time, job suspension/restart is not much used in practice at supercomputer centers for parallel job scheduling. A number of questions remain unanswered regarding the practical utility of pre-emptive scheduling. We explore this issue through a simulation-based study, using job logs from a supercomputer center We develop a tunable selective-suspension strategy, and demonstrate its effectiveness. We also present new insights into the effect of pre-emptive scheduling on different job classes and address the impact of suspensions on worst-case slowdown.

Feedback control for real-time scheduling

Abstract: Most real-time scheduling algorithms are open-loop algorithms as the scheduling decisions are based on the worst-case estimates of task parameters. In recent years, the "closed-loop" scheduling has gained importance due to its applicability to many real-world problems wherein the feedback information can be exploited efficiently to adjust task and/or scheduler parameters, thereby improving the system's performance. In this paper, we discuss an open-loop dynamic scheduling algorithm that employs a notion of task overlap in the scheduler in order to provide some flexibility in task execution time. Then we present a novel closed-loop approach for dynamically estimating the execution time of tasks based on both deadline miss ratio and task rejection ratio in the system. This approach is highly preferable for firm/soft real-time systems since it provides a firm performance guarantee in terms of deadline misses while achieving a high guarantee ratio. We design the proportional-integral controller and H/sub /spl infin// controller for closed loop scheduling. We evaluate the performance of the open-loop and the closed-loop approaches using simulation studies. We show that the closed-loop dynamic scheduling offers a better performance over the open-loop scheduling under all practical conditions.

Preemptive multiprocessor scheduling anomalies

Abstract: Preemptive scheduling of periodically arriving tasks on a multiprocessor is considered. We show that many common multiprocessor real-time scheduling algorithms suffer from scheduling anomalies, that is, deadlines are originally met, but a decrease in execution times or an increase in periods of tasks can cause deadlines to be missed. We propose a partitioned multiprocessor fixed-priority scheduling algorithm with the prominent features that (i) it does not suffer from such scheduling anomalies and (ii) if less than 41% of the capacity is used then deadlines are met.