Abstract. We consider the Windows Scheduling problem. The problem is a restricted version of Unit-Fractions Bin Packing, and it is also called Inventory Replenishment in the context of Supply Chain. In brief, the problem is to schedule the use of communication channels to clients. Each client ci is characterized by an active cycle and a window wi. During the period of time that any given client ci is active, there must be at least one transmission from ci scheduled in any wi consecutive time slots, but at most one transmission can be carried out in each channel per time slot. The goal is to minimize the number of channels used.We extend previous online models, where decisions are permanent, assuming that clients may be reallocated at some cost. We assume that such cost is a constant amount paid per reallocation. That is, we aim to minimize also the number of reallocations. We present three online reallocation algorithms for Windows Scheduling. We evaluate experimentally these protocols showing that, in practice, all three achieve constant amortized reallocations with close to optimal channel usage. Our simulations also expose interesting trade-offs between reallocations and channel usage. We introduce a new objective function for WS with reallocations, that can be also applied to models where reallocations are not possible. We analyze this metric for one of the algorithms which, to the best of our knowledge, is the first online WS protocol with theoretical guarantees that applies to scenarios where clients may leave and the analysis is against current load rather than peak load. Using previous results, we also observe bounds on channel usage for one of the algorithms.
resources We provide abstract interfaces, amenable to both users and applications, through (virtual) file trees. Unlike other systems that use files for interfaces (Plan 9, for example), we don't provide pixmaps or other low-level artifacts to support GUIs. We support user interfaces by providing a file tree in which a different file represents each UI element (that is, widget). The same applies to other resources.These files aren't on disk but are provided by resource servers, such as in Plan 9 or Unix's /proc. 3 In addition, we don't propose to intercept file system calls. Rather, we take the Plan 9 approach to the limit and provide all services by implement-
Plan B maps abstract interfaces to files and adapts to file tree availability. It is easy to program, offers a general-purpose computing environment, and supports smart spaces without using middleware.The system ensures that the namespace reflects which resources are available and which ones aren't, cleanly removing unavailable resources from the file trees. JULY-SEPTEMBER 2007 PERVASIVE computing 63 Figure 2. A typical Plan B screen, serviced by the Omero UI volume.
SUMMARYThe main purpose of the present study is to analyze the suitability of performance-based scheduling strategies for High Throughput Computing applications applied to Federated Grids consisting of several Grid infrastructures. The infrastructures forming aFederated Grid are classified as internal or external. This is because our scheduling policies map as much jobs as possible first to internal resources. In this way the mapping strategies save time and communication bandwidth by exploiting the location of the internal resources and the membership to their respective resource domains. At the same time, the policies avoid overloading external resources facilitating the cooperation between organizations to share resources. In this paper we consider three new algorithms for scheduling in situations where there are several Grid infrastructures of different types: enterprise, partner, or utility.
Abstract. In this paper we present a dynamic mapping strategy for scheduling independent tasks in Federated Grids. This strategy is performed in two steps: first we calculate a new objective, and then we apply advance scheduling to meet the new objective. The results obtained by simulation show that the combination of these two steps reduces the makespan and increases the throughput. Thus, the mapping strategy proposed meets two of the most common objective functions of tasks scheduling problems: makespan and performance of the resources. The presented algorithm is easy to implement, unlike Genetic Algorithms is fast enough to be used in a realistic scheduling, and is efficient. In addition, the information the strategy needs can be provided by any Grid Information Service, and its does not require the deployment of complex prediction services or service level agreement: it can work in any Grid.
There is a huge effort in ongoing research on new middleware platforms and new distributed services to support ubiquitous environments and pervasive applications. Most research projects mention concrete applications or demonstrators used to back up the claimed need for a new particular service, piece of software, or middleware layer. However, we have found that in many cases we could easily build such applications by relying on services already provided by the system we use daily, Plan 9 from Bell Labs. This paper explores how far can we go with a traditional system to support an ubiquitous environment, with no need for new services. We describe how we used Plan 9 to make our environment become ubiquitous. We describe as well what limits we found, and what technology could be used to overcome them.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.