Weighted Scheduling of Time-Sensitive Coflows

TL;DR

This paper presents extbackslash wdcoflow, a novel weighted scheduling algorithm for coflows in datacenter networks that prioritizes deadline adherence, significantly improving the number of coflows meeting their deadlines compared to existing solutions.

Contribution

Introduces extbackslash wdcoflow, a new heuristic algorithm combining dynamic programming and inequalities for deadline-aware coflow scheduling with weighted prioritization.

Findings

extbackslash wdcoflow outperforms state-of-the-art by up to 3x in deadline meeting rate.

The algorithm improves class-based admission rates by up to 4x.

Demonstrates significant gains in weighted coflow admission in simulations.

Abstract

Datacenter networks commonly facilitate the transmission of data in distributed computing frameworks through coflows, which are collections of parallel flows associated with a common task. Most of the existing research has concentrated on scheduling coflows to minimize the time required for their completion, i.e., to optimize the average dispatch rate of coflows in the network fabric. Nevertheless, modern applications often produce coflows that are specifically intended for online services and mission-crucial computational tasks, necessitating adherence to specific deadlines for their completion. In this paper, we introduce \wdcoflow,~ a new algorithm to maximize the weighted number of coflows that complete before their deadline. By combining a dynamic programming algorithm along with parallel inequalities, our heuristic solution performs at once coflow admission control and coflow prioritization, imposing a $\sigma$-order on the set of coflows. With extensive simulation, we demonstrate the effectiveness of our algorithm in improving up to $3\times$ more coflows that meet their deadline in comparison the best SoA solution, namely $\mathtt{CS\text{-}MHA}$. Furthermore, when weights are used to differentiate coflow classes, \wdcoflow~ is able to improve the admission per class up to $4\times$, while increasing the average weighted coflow admission rate.