Homa: A Receiver-Driven Low-Latency Transport Protocol Using Network Priorities (Complete Version)

TL;DR

Homa is a receiver-driven transport protocol for datacenter networks that achieves ultra-low latency for short messages, high bandwidth utilization, and better scalability than existing protocols through network priorities and dynamic flow control.

Contribution

Homa introduces a novel receiver-driven protocol with in-network priority queues and dynamic bandwidth management, significantly reducing latency and increasing load capacity.

Findings

99th percentile RTTs less than 15μs at 80% load on 10 Gbps network

Latency comparable to pFabric and better than pHost, PIAS, and NDP

Homa sustains higher network loads than competing protocols

Abstract

Homa is a new transport protocol for datacenter networks. It provides exceptionally low latency, especially for workloads with a high volume of very short messages, and it also supports large messages and high network utilization. Homa uses in-network priority queues to ensure low latency for short messages; priority allocation is managed dynamically by each receiver and integrated with a receiver-driven flow control mechanism. Homa also uses controlled overcommitment of receiver downlinks to ensure efficient bandwidth utilization at high load. Our implementation of Homa delivers 99th percentile round-trip times less than 15{\mu}s for short messages on a 10 Gbps network running at 80% load. These latencies are almost 100x lower than the best published measurements of an implementation. In simulations, Homa's latency is roughly equal to pFabric and significantly better than pHost, PIAS, and NDP for almost all message sizes and workloads. Homa can also sustain higher network loads than pFabric, pHost, or PIAS.