Loading...
Please wait, while we are loading the content...
Similar Documents
Statistical properties of task running times in a global-scale grid environment (2005)
| Content Provider | CiteSeerX |
|---|---|
| Author | De Boelelaan, A. Dobber, Menno |
| Abstract | Abstract — Over the years, the use of global grid environments have become widespread. In order to make applications robust against the dynamics of those grid environments it is essential to develop powerful techniques. For these techniques to be effective, it is important to have an understanding of the statistical properties of the dynamics of a grid environment. Today, however, the statistical properties of the dynamic behavior of real globalscale grid environments are not well understood. Therefore, we present a framework of statistical analysis tools by which we are able to obtain a characterization for different properties of different types of grid environments. Our main focus is on highly CPU-intensive grid applications that require huge amounts of processor power for running tasks. In order to derive a characterization of the statistical properties of the running times of tasks on processors, we have performed extensive measurements in a real, global-scale grid environment and analyzed the results of the framework of analyses. We observe (1) a strong burstiness of the running times over different time scales, (2) a strong heterogeneity of the running-time characteristics among the different hosts, (3) a strong heterogeneity of the running-time characteristics for the same host over different time intervals, and (4) the occurrence of sudden level-switches in the running times, amongst others. These observations are used to develop effective techniques for the prediction of running times. They can be used to develop effective control schemes for robust grid applications. ACKNOWLEDGMENT The authors would like to thank Mathijs den Burger, Thilo Kielmann, and Henri Bal, for their useful comments. I. |
| File Format | |
| Publisher Date | 2005-01-01 |
| Access Restriction | Open |
| Subject Keyword | Statistical Property Huge Amount Main Focus Sudden Level-switches Different Time Scale Henri Bal Running Time Mathijs Den Burger Statistical Analysis Tool Processor Power Thilo Kielmann Effective Technique Different Time Interval Dynamic Behavior Amongst Others Global Grid Environment Real Globalscale Grid Environment Different Host Extensive Measurement Powerful Technique Robust Grid Application Different Property Strong Burstiness Cpu-intensive Grid Application Effective Control Scheme Running-time Characteristic Grid Environment Global-scale Grid Environment Strong Heterogeneity Useful Comment |
| Content Type | Text |
