TEL: Low-Latency Failover Traffic Engineering in Data Plane

TL;DR

TEL introduces two low-latency failover traffic engineering mechanisms for programmable data planes, significantly improving flow completion times during network failures in datacenter environments.

Contribution

The paper presents TEL, a novel system with control-plane and data-plane FRR mechanisms that are memory-efficient and compatible with modern line-rate architectures.

Findings

TEL improves flow completion time by up to 7.3x for small flows.

TEL achieves up to 12x faster recovery for large flows.

The mechanisms are implemented on P4 switches and tested on various topologies.

Abstract

Modern network applications demand low-latency traffic engineering in the presence of network failure while preserving the quality of service constraints like delay and capacity. Fast Re-Route (FRR) mechanisms are widely used for traffic re-routing purposes in failure scenarios. Control plane FRR typically computes the backup forwarding rules to detour the traffic in the data plane when the failure occurs. This mechanism could be computed in the data plane with the emergence of programmable data planes. In this paper, we propose a system (called TEL) that contains two FRR mechanisms, namely, TEL-C and TEL-D. The first one computes backup forwarding rules in the control plane, satisfying max-min fair allocation. The second mechanism provides FRR in the data plane. Both algorithms require minimal memory on programmable data planes and are well-suited with modern line rate match-action forwarding architectures (e.g., PISA). We implement both mechanisms on P4 programmable software switches (e.g., BMv2 and Tofino) and measure their performance on various topologies. The obtained results from a datacenter topology show that our FRR mechanism can improve the flow completion time up to 4.6x$-$7.3x (i.e., small flows) and 3.1x$-$12x (i.e., large flows) compared to recirculation-based mechanisms, such as F10, respectively.