Congestion Management in High-Performance Interconnection Networks Using Adaptive Routing Notifications

TL;DR

This paper introduces a novel congestion management strategy for high-performance interconnection networks that uses adaptive routing notifications to effectively isolate and mitigate congestion, improving overall network performance.

Contribution

The paper proposes a new congestion management approach leveraging existing adaptive routing notifications to better isolate congesting flows in high-performance networks.

Findings

Reduces congestion spreading in network simulations

Improves network throughput and latency

Effectively isolates congesting flows

Abstract

The interconnection network is a crucial subsystem in High-Performance Computing clusters and Data-centers, guaranteeing high bandwidth and low latency to the applications' communication operations. Unfortunately, congestion situations may spoil network performance unless the network design applies specific countermeasures. Adaptive routing algorithms are a traditional approach to dealing with congestion since they provide traffic flows with alternative routes that bypass congested areas. However, adaptive routing decisions at switches are typically based on local information without a global network traffic perspective, leading to congestion spreading throughout the network beyond the original congested areas. In this paper, we propose a new efficient congestion management strategy that leverages adaptive routing notifications currently available in some interconnect technologies and efficiently isolates the congesting flows in reserved spaces at switch buffers. The experiment results based on simulations of realistic traffic scenarios show that our proposal removes the congestion impact.