• Corpus ID: 1072596

Stateless Network Functions: Breaking the Tight Coupling of State and Processing

  title={Stateless Network Functions: Breaking the Tight Coupling of State and Processing},
  author={Murad Kaplan and Azzam Alsudais and Eric Keller and Franck Le},
  booktitle={Symposium on Networked Systems Design and Implementation},
In this paper we present Stateless Network Functions, a new architecture for network functions virtualization, where we decouple the existing design of network functions into a stateless processing component along with a data store layer. [] Key Method A network-wide orchestrator monitors the instances for load and failure, manages instances to scale and provide resilience, and leverages an OpenFlow-based network to direct traffic to instances.

Figures and Tables from this paper

Industrial-Scale Stateless Network Functions

This paper proposes a system design that can be adapted to any telco use case without the need for complex coordination among the network control, the stateless network functions, and the state storage backend, and shows that in certain cases the design outperforms the state-of-the-art significantly.

libVNF: Building Virtual Network Functions Made Easy

Network Function Virtualization (NFV) aims to reduce costs and increase flexibility of networks by moving functionality traditionally implemented in custom hardware into software packet processing

Correctness and Performance for Stateful Chained Network Functions

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

FTvNF: fault tolerant virtual network functions

This paper's approach significantly reduces the latency overhead incurred by the network elements, both in failure-free operations and when failures occur, and better suits the common case of NFV service chaining, as the mechanisms are applied once per chain, thus significantly improve the performance over approaches that treat each VNF separately.

TEA: Enabling State-Intensive Network Functions on Programmable Switches

A new system architecture, called TEA (Table Extension Architecture), provides a virtual table abstraction that allows NFs on programmable switches to look up large virtual tables built on external DRAM and enables switch ASICs to access externalDRAM purely in the data plane without involving CPUs on servers.

Elastic scaling of P4 network functions

A novel, horizontal scaling solution for Virtualized Network Functions (VNFs) was designed and implemented in P4 and reduced migration times by 0.52s on average while the average latency observed by the flow is reduced by approximately 5ms on average when compared to current state­ of­the­art.

Dyssect: Dynamic Scaling of Stateful Network Functions

Dyssect is presented, a system that enables dynamic scaling of stateful NFs by disaggregating the states of network functions by carefully coordinating actions between cores and a central controller.

Re-Architecting NFV Ecosystem with Microservices: State of the Art and Research Challenges

The case is made for using the microservice software architecture, proven to be effective for building large-scale cloud applications from reusable and independently deployable components, to re-architect the NFV ecosystem through modular VNF design and flexible service composition.

Elastic Slicing in Programmable Networks

A custom scaling protocol and framework is developed that can consistently, with negli-gible delay, scale network slices and functions transparently to the slice end-users and is compared to state-of-the-art scaling techniques.

A Disaggregated Packet Processing Architecture for Network Function Virtualization

MicroNF, a disaggregated packet processing architecture facilitating the deployment of VNFs and SFCs using reusable, loosely-coupled, and independently deployable components, is proposed, including the different architecture components and optimizations for improving packet processing throughput and latency.



Stateless Network Functions

This paper proposes that network functions should be similarly redesigned to be stateless, and describes how stateless network functions can leverage recent advances in low-latency network systems to achieve acceptable performance.

NetVM: High Performance and Flexible Networking Using Virtualization on Commodity Platforms

This evaluation shows how NetVM can compose complex network functionality from multiple pipelined VMs and still obtain throughputs up to 10 Gbps, an improvement of more than 250% compared to existing techniques that use SR-IOV for virtualized networking.

Split/Merge: System Support for Elastic Execution in Virtual Middleboxes

A state-centric, systems-level abstraction for elastic middleboxes called Split/Merge is presented, which enables load-balanced elasticity and enables a 25% reduction in maximum latency while eliminating hotspots during scale-out and a 50% quicker scale-in than standard approaches.

netmap: A Novel Framework for Fast Packet I/O

  • L. Rizzo
  • Computer Science
    USENIX Annual Technical Conference
  • 2012
The novelty in the proposal is not only that it exceeds the performance of most of previous work, but also that it provides an architecture that is tightly integrated with existing operating system primitives, not tied to specific hardware, and easy to use and maintain.

Design and Implementation of a Consolidated Middlebox Architecture

CoMb is presented, a new architecture for middlebox deployments that systematically explores opportunities for consolidation, both at the level of building individual middleboxes and in managing a network of middleboxes.

Pico replication: a high availability framework for middleboxes

Pico Replication is proposed, a system-level framework for middleboxes that exploits their flow-centric structure to achieve low overhead, fully customizable HA, and leverages OpenFlow to provide near instant flow-level failure recovery.

Demystifying the dark side of the middle: a field study of middlebox failures in datacenters

It is found that middlebox failures are prevalent and they can significantly impact hosted services, and current middlebox proposals are analyzed based on the study.

Maglev: A Fast and Reliable Software Network Load Balancer

Maglev is Google's network load balancer, a large distributed software system that runs on commodity Linux servers that is specifically optimized for packet processing performance.

Improving the Safety, Scalability, and Efficiency of Network Function State Transfers

This work proposes two novel enhancements, packet reprocessing and peer-to-peer transfers, to address packet buffering issues and shows they reduce the average per-packet latency overhead and state transfer times by up to 70% and 92% respectively.

Seamless BGP Migration with Router Grafting

R router grafting, where parts of a router are seamlessly removed from one router and merged into another, is presented, and it is shown that grafting a BGP session is practical even with today's monolithic router software.