Correctness and Performance for Stateful Chained Network Functions

TL;DR

This paper introduces ame, a framework for NFV that ensures correct state management and high performance in NF chains, supporting 10Gbps throughput with minimal latency increase.

Contribution

It presents a novel NFV framework with external state store and algorithms that maintain correctness and performance during dynamic NF chain operations and failures.

Findings

Supports ~10Gbps per-NF throughput

Less than 0.6 microseconds latency increase

Maintains chain-wide correctness with minimal overhead

Abstract

Network functions virtualization (NFV) allows operators to employ NF chains to realize custom policies, and dynamically add instances to meet demand or for failover. NFs maintain detailed per- and cross-flow state which needs careful management, especially during dynamic actions. Crucially, state management must: (1) ensure NF chain-wide correctness and (2) have good performance. To this end, we built \name, an NFV framework that leverages an external state store coupled with state management algorithms and metadata maintenance for correct operation even under a range of failures. Our evaluation shows that CHC can support ~10Gbps per-NF throughput and <0.6mus increase in median per-NF packet processing latency, and chain-wide correctness at little additional cost.