Efficient task pruning mechanism to improve robustness of heterogeneous computing systems

Abstract

In heterogeneous distributed computing (HC) systems, diversity can exist in both computational resources and arriving tasks. In an inconsistently heterogeneous computing system, task types have different execution times on heterogeneous machines. A method is required to map arriving tasks to machines based on machine availability and performance, maximizing the number of tasks meeting deadlines (defined as robustness). For tasks with hard deadlines (e.g., those in live video streaming), tasks that miss their deadlines are dropped. The problem investigated in this research is maximizing the robustness of an oversubscribed HC system. A way to maximize this robustness is to prune (i.e., defer or drop) tasks with low probability of meeting their deadlines to increase the probability of other tasks meeting their deadlines. In this paper, we first provide a mathematical model to estimate a task’s probability of meeting its deadline in the presence of task dropping. We then investigate methods for engaging probabilistic dropping. We propose methods to dynamically determine task dropping and deferring threshold probabilities. Next, we develop a pruning system and a pruning-aware mapping heuristic, which we extend to engender fairness across various task types. We present the pruning mechanism as an independent component that can be applied to any mapping heuristic to improve the system robustness. To reduce overhead of the pruning mechanism, we propose approximation methods that remarkably reduce the number of mathematical calculations and improve the practicality of deploying the mechanism in heterogeneous or even homogeneous computing systems. We show the cost and energy gains of the pruning mechanism. Simulation results, harnessing a selection of mapping heuristics, show efficacy of the pruning mechanism in improving robustness (on average by ≃22%) and cost in an oversubscribed HC system by up to ≃33%.