DCoflow: Deadline-Aware Scheduling Algorithm for Coflows in Datacenter Networks

TL;DR

DCoflow is a lightweight, deadline-aware scheduling algorithm for coflows in datacenter networks, designed to maximize the number of coflows meeting their deadlines, especially for time-critical applications.

Contribution

Introduces DCoflow, a novel online joint admission control and scheduling algorithm that improves deadline adherence for coflows in datacenter networks.

Findings

Outperforms existing scheduling solutions in numerical evaluations

Increases the number of coflows meeting their deadlines

Efficiently handles time-critical coflows in real-world scenarios

Abstract

Datacenter networks routinely support the data transfers of distributed computing frameworks in the form of coflows, i.e., sets of concurrent flows related to a common task. The vast majority of the literature has focused on the problem of scheduling coflows for completion time minimization, i.e., to maximize the average rate at which coflows are dispatched in the network fabric. Modern applications, though, may generate coflows dedicated to online services and mission-critical computing tasks which have to comply with specific completion deadlines. In this paper, we introduce $\mathtt{DCoflow}$, a lightweight deadline-aware scheduler for time-critical coflows in datacenter networks. The algorithm combines an online joint admission control and scheduling logic and returns a $\sigma$-order schedule which maximizes the number of coflows that attain their deadlines. Extensive numerical results demonstrate that the proposed solution outperforms existing ones.