Parking Packet Payload with P4

TL;DR

PayloadPark is a novel in-network optimization that temporarily stores packet payloads in programmable switches to improve network function throughput and reduce bandwidth consumption, without latency penalties.

Contribution

Introducing PayloadPark, a P4-based system that enhances NF performance by parking payloads in switch memory, demonstrated on a Barefoot Tofino ASIC with significant throughput gains.

Findings

Improves goodput by up to 36% for firewalls and NATs.

Reduces data transmission between switch and NF server by up to 58%.

Supports up to 8 NF servers with minimal on-chip memory usage.

Abstract

Network Function (NF) deployments suffer from poor link goodput, because popular NFs such as firewalls process only packet headers while receiving and transmitting complete packets. As a result, unnecessary packet payloads needlessly consume link bandwidth. We introduce PayloadPark, which improves goodput by temporarily parking packet payloads in the stateful memory of dataplane programmable switches. PayloadPark forwards only packet headers to NF servers, thereby saving bandwidth between the switch and the NF server. PayloadPark is a transparent in-network optimization that complements existing approaches for optimizing NF performance on end-hosts. We prototyped PayloadPark on a Barefoot Tofino ASIC using the P4 language. Our prototype, when deployed on a top-of-rack switch, can service up to 8 NF servers using less than 40% of the on-chip memory resources. The prototype improves goodput by 10- 36% for Firewall and NAT NFs and by 10-26% for a Firewall -> NAT NF chain without harming latency. The prototype also reduces PCIe bus load by 2-58% on the NF server thanks to the reduced data transmission between the switch and the NF server. With workloads that have datacenter network traffic characteristics, PayloadPark provides a 13% goodput gain with the Firewall -> NAT -> LB NF chain without latency penalty. In the same setup, we can further increase the goodput gain to 28% by using packet recirculation.