Abstract not found

This paper evaluates linear models for predicting the Digital Unix five-second host load average from 1 to 30 seconds into the future. A detailed statistical study of a large number of long, fine grain load traces from a variety of real machines leads to consideration of the Box-Jenkins models (AR, MA, ARMA, ARIMA), and the ARFIMA models (due to self-similarity.) We also consider a simple windowed-mean model. The computational requirements of these models span a wide range, making some more practical than others for incorporation into an online prediction system. We rigorously evaluate the predictive power of the models by running a large number of randomized testcases on the load traces and then data-mining their results. The main conclusions are that load is consistently predictable to a very useful degree, and that the simple, practical models such as AR are sufficient for host load prediction. We recommend AR(16) models or better for host load prediction. We implement an online host load prediction system around the AR(16) model and evaluate its overhead, finding that it uses miniscule amounts of CPU time and network bandwidth

Abstract—RPS is a publicly available toolkit that allows a practitioner to straightforwardly create flexible online and offline resource prediction systems in which resources are represented by independent, periodically sampled, scalar-valued measurement streams. The systems predict the future values of such streams from past values and are composed at runtime out of a large and extensible set of communicating components that are in turn constructed using RPS’s extensible sensor, prediction, wavelet, and communication libraries. This paper describes the design, implementation, and performance of RPS. We have used RPS extensively to evaluate predictive models and build online prediction systems for host load, Windows performance data, and network bandwidth. The computation and communication overheads involved in such systems are quite low. Index Terms—Distributed systems, performance of systems. æ 1

This paper evaluates linear models for predicting the Digital Unix five-second load average from 1 to 30 seconds into the future. A detailed statistical study of a large number of load traces leads to consideration of the Box-Jenkins models (AR, MA, ARMA, ARIMA), and the ARFIMA models (due to self-similarity.) These models, as well as a simple windowed-mean scheme, are evaluated by running a large number of randomized testcases on the load traces. The main conclusions are that load is consistently predictable to a useful degree, and that the simpler models such as AR are sufficient for doing this prediction.

We describe and evaluate the Running Time Advisor (RTA), a system that can predict the running time of a compute-bound task on a typical shared, unreserved commodity host. The prediction is computed from linear time series predictions of host load and takes the form of a confidence interval that neatly expresses the error associated with the measurement and prediction processes--- error that must be captured to make statistically valid decisions based on the predictions. Adaptive applications make such decisions in pursuit of consistent high performance, choosing, for example, the host where a task is most likely to meet its deadline. We begin by describing the system and summarizing the results of our previously published work on host load prediction. We then describe our algorithm for computing predictions of running time from host load predictions. Finally, we evaluate the system using over 100,000 randomized testcases run on 39 different hosts.

The term "Grid" has become common parlance among parallel and distributed computer scientists to denote a middleware infrastructure for wide-area scientific and engineering computing. The discussion of standards and best practices is ongoing in the Grid Forum community to identify key pieces of the middleware infrastructure. One of the areas under discussion is different models for grid information services.

... In this paper, we show why interactive mobile applications require us to rethink this concept from first principles. Such applications are difficult to support because they place heavy resource demands on hardware that is typically optimized for weight, size and battery life rather than compute power. We show how the notion of an algorithm can be extended to help alleviate this problem, and examine the implications of this shift in viewpoint. The paper is organized in three parts: rationale, research agenda, and related work.

Abstract not found

The real-time scheduling advisor (RTSA) is an entirely userlevel system that an application running on a typical shared, unreserved distributed computing environment can turn to for advice on how to schedule its compute-bound soft real-time tasks. Given a list of hosts, a description of the CPU demands of the task, the deadline, and a confidence level, the RTSA will recommend one of the hosts and predict, as a confidence interval, the running time of the task on that host. The RTSA is based on a scalable and extensible shared resource prediction system based on statistical time series analysis. In this paper, we first describe how the RTSA builds on this underlying system to provide its service, and then we evaluate its performance using a randomized methodology based on real background workloads, determining the effect of different factors. We also compare it with a random approach and a measurement-based approach.

We present the design and implementation of the Virtual Microscope, a software system employing a client/server architecture to provide a realistic emulation of a high power light microscope. The system provides a form of completely digital telepathology, allowing simultaneous access to archived digital slide images by multiple clients. The main problem the system targets is storing and processing the extremely large quantities of data required to represent a collection of slides. The Virtual Microscope client software runs on the end user's PC or workstation, while database software for storing, retrieving and processing the microscope image data runs on a parallel computer or on a set of workstations at one or more potentially remote sites. We have designed and implemented two versions of the data server software. One implementation is a customization of a database system framework that is optimized for a tightly coupled parallel machine with attached local disks. The second implementation is component-based, and has been designed to accommodate access to and processing of data in a distributed, heterogeneous environment. We also have developed caching client software, implemented in Java, to achieve good response time and portability across different computer platforms. The performance results presented show that the Virtual Microscope systems scales well, so that many clients can be adequately serviced by an appropriately configured data server.