Estimation of the latency of a production grid over several weeks

[摘要] In this paper, we study grid job submission latencies. Together with outliers, the latency highly impacts performances on production grids, due to its high values and variations. It is particularly prejudicial for determining the expected duration of applications handling a high number of jobs. In previous work, a probabilistic model of the latency has been used to estimate an optimal timeout value considering a given distribution of jobs latencies. This timeout value is then used in a job resubmission strategy. The purpose of this paper is to evaluate to what extent updating this model with relevant contextual parameters can help to refine the latency estimation. In the first part of the paper, we study the validity of parameters along several weeks. Experiments on the EGEE grid show that performance can be improved by the update of model parameters. In the second part, we study the influence of the resource broker or the computing site and the day of the week. We experimentally show that some of them have a statistically significant influence on the jobs latency. We exploit this con- textual information in the perspective of proposing a reliable job submission strategy.

[学科分类] 计算机科学（综合）

[关键词] Grid Computing;Model;Context