PABO: Mitigating Congestion via Packet Bounce in Data Center Networks

TL;DR

PABO is a link-layer congestion mitigation technique for data center networks that temporarily bounces packets upstream to reduce delays and handle transient congestion without end-device intervention.

Contribution

This paper introduces PABO, a novel link-layer design that mitigates congestion by bouncing packets upstream, providing per-flow control and congestion feedback without relying on end devices.

Findings

PABO effectively reduces transient congestion in data center networks.

PABO significantly decreases end-to-end delay during congestion events.

PABO outperforms traditional methods in handling short-term traffic bursts.

Abstract

In today's data center, a diverse mix of throughput-sensitive long flows and delay-sensitive short flows are commonly presented in shallow-buffered switches. Long flows could potentially block the transmission of delay-sensitive short flows, leading to degraded performance. Congestion can also be caused by the synchronization of multiple TCP connections for short flows, as typically seen in the partition/aggregate traffic pattern. While multiple end-to-end transport-layer solutions have been proposed, none of them have tackled the real challenge: reliable transmission in the network. In this paper, we fill this gap by presenting PABO -- a novel link-layer design that can mitigate congestion by temporarily bouncing packets to upstream switches. PABO's design fulfills the following goals: i) providing per-flow based flow control on the link layer, ii) handling transient congestion without the intervention of end devices, and iii) gradually back propagating the congestion signal to the source when the network is not capable to handle the congestion.Experiment results show that PABO can provide prominent advantage of mitigating transient congestions and can achieve significant gain on end-to-end delay.