Abstract. We investigate the power of online algorithms and mechanisms for two different classic models of preemptive online job scheduling. These two models are resumptive and non-resumptive job scheduling. The distinction is when we decide to allocate a previously preempted job. In the resumptive

;compact" search of the huge space of all possible schedulings. This search for "bad" schedulings is done by allowing the user to change the simulation parameters, in particular the context-switch delay and the scheduling policy. The paper includes a set of typical experiments with the simulator

note that in wireless networks, an important role of resource allocation is to balance the system performance and fairness among "good" and "bad" users. We propose three heuristic timefraction assignment schemes, which approach the problem from different viewpoints. Keywords---Scheduling

: multiprocessor scheduling. After surveying several important papers and recent work in the field, I argue for a move away from traditional, centralized schemes limited to the scheduling of loop-derived parallelism. In order to gain insight into the complexity required for good scheduler performance in large

An instance of a shop-scheduling problem is given by a set of structural data (operation set, precedence relations, ...), numerical data (processing times, release dates, ...) and an objective function. A feasible (i.e., acyclic) combination of all job orders and machine orders is called a sequence

Large IT service providers comprise hundreds or even thousands of system administrators to handle customers ’ IT infrastructure. As part of the Information Systems that support the decision making of this environment, Incident Management Systems are used and usually provide human resource assignment functionalities. However, the assignment poses several challenges, such as establishing priorities to tasks and defining when and how tasks are allocated to available system administrators. This paper describes a set of incident dispatching policies that can be used, and by using workloads from different departments of an IT service provider, this work evaluates the impact of task preemption on incident resolution and service level agreement attainment. 1

Disk head scheduling is a standard topic in undergraduate operat-ing systems courses. Disk drives were once fairly simple devices with little intelligence. Disk head scheduling and bad block map-ping were done exclusively by operating systems. As disk drives became larger and faster, they took

ensuring a given mean squared error (mse) performance. The proposed power scheduling scheme suggests that the sensors with bad channels or poor observation qualities should decrease their quantization resolutions or simply become inactive in order to save power. For the remaining active sensors

propose a new measure disturbance in order to comprise the intrinsic difficulty of finding a short schedule for a problem instance. Previously known approaches suffer from extremely bad performance in certain network scenarios even if disturbance is low. To overcome this problem, we present a novel

"hard" is it to partition threads and how "bad" will a heuristic partitioning algorithm be? We propose a cost model for both multithreaded machines and user programs, and we formulate the thread partition problem as an optimization problem. Then, we answer the above two questions