Network function virtualization (NFV) has drawn significant attention from both industry and academia as an important shift in telecommunication service provisioning. By decoupling network functions (NFs) from the physical devices on which they run, NFV has the potential to lead to significant reductions in operating expenses (OPEX) and capital expenses (CAPEX) and facilitate the deployment of new services with increased agility and faster time-to-value. The NFV paradigm is still in its infancy and there is a large spectrum of opportunities for the research community to develop new architectures, systems and applications, and to evaluate alternatives and trade-offs in developing technologies for its successful deployment. In this paper, after discussing NFV and its relationship with complementary fields of software defined networking (SDN) and cloud computing, we survey the state-of-the-art in NFV, and identify promising research directions in this area. We also overview key NFV projects, standardization efforts, early implementations, use cases, and commercial products.

/pdf/network-function-virtualization-state-of-the-art-and-29gg3feprt.pdf

Network Function Virtualization: State-of-the-Art and Research Challenges

The basic building block of ever larger data centers has shifted from a rack to a modular container with hundreds or even thousands of servers. Delivering scalable bandwidth among such containers is a challenge. A number of recent efforts promise full bisection bandwidth between all servers, though with significant cost, complexity, and power consumption. We present Helios, a hybrid electrical/optical switch architecture that can deliver significant reductions in the number of switching elements, cabling, cost, and power consumption relative to recently proposed data center network architectures. We explore architectural trade offs and challenges associated with realizing these benefits through the evaluation of a fully functional Helios prototype.

/pdf/helios-a-hybrid-electrical-optical-switch-architecture-for-3pk00vbyfq.pdf

Helios: a hybrid electrical/optical switch architecture for modular data centers

We present the first large-scale analysis of failures in a data center network. Through our analysis, we seek to answer several fundamental questions: which devices/links are most unreliable, what causes failures, how do failures impact network traffic and how effective is network redundancy? We answer these questions using multiple data sources commonly collected by network operators. The key findings of our study are that (1) data center networks show high reliability, (2) commodity switches such as ToRs and AggS are highly reliable, (3) load balancers dominate in terms of failure occurrences with many short-lived software related faults,(4) failures have potential to cause loss of many small packets such as keep alive messages and ACKs, and (5) network redundancy is only 40% effective in reducing the median impact of failure.

/pdf/understanding-network-failures-in-data-centers-measurement-42rwx1vkms.pdf

Understanding network failures in data centers: measurement, analysis, and implications

Modern day datacenters host hundreds of thousands of servers that coordinate tasks in order to deliver highly available cloud computing services. These servers consist of multiple hard disks, memory modules, network cards, processors etc., each of which while carefully engineered are capable of failing. While the probability of seeing any such failure in the lifetime (typically 3-5 years in industry) of a server can be somewhat small, these numbers get magnified across all devices hosted in a datacenter. At such a large scale, hardware component failure is the norm rather than an exception.Hardware failure can lead to a degradation in performance to end-users and can result in losses to the business. A sound understanding of the numbers as well as the causes behind these failures helps improve operational experience by not only allowing us to be better equipped to tolerate failures but also to bring down the hardware cost through engineering, directly leading to a saving for the company. To the best of our knowledge, this paper is the first attempt to study server failures and hardware repairs for large datacenters. We present a detailed analysis of failure characteristics as well as a preliminary analysis on failure predictors. We hope that the results presented in this paper will serve as motivation to foster further research in this area.

/pdf/characterizing-cloud-computing-hardware-reliability-2k07m4tjcs.pdf

Characterizing cloud computing hardware reliability

Maglev is Google's network load balancer. It is a large distributed software system that runs on commodity Linux servers. Unlike traditional hardware network load balancers, it does not require a specialized physical rack deployment, and its capacity can be easily adjusted by adding or removing servers. Network routers distribute packets evenly to the Maglev machines via Equal Cost Multipath (ECMP); each Maglev machine then matches the packets to their corresponding services and spreads them evenly to the service endpoints. To accommodate high and ever-increasing traffic, Maglev is specifically optimized for packet processing performance. A single Maglev machine is able to saturate a 10Gbps link with small packets. Maglev is also equipped with consistent hashing and connection tracking features, to minimize the negative impact of unexpected faults and failures on connection-oriented protocols. Maglev has been serving Google's traffic since 2008. It has sustained the rapid global growth of Google services, and it also provides network load balancing for Google Cloud Platform.

/pdf/maglev-a-fast-and-reliable-software-network-load-balancer-2lgd4mdc84.pdf

Maglev: a fast and reliable software network load balancer

There has been a recent interest in modularized shipping containers as the building block for data centers. However, there are no published results on the different design tradeoffs it offers. In this paper we investigate a model where such a container is never serviced during its deployment lifetime, say 3 years, for hardware faults. Instead, the hardware is over-provisioned in the beginning and failures are handled gracefully by software. The reasons vary from ease of accounting and management to increased design flexibility owing to its sealed and service-free nature. We present a preliminary model for performance, reliability and cost for such service-less containerized solutions. There are a number of design choices/policies for over-provisioning the containers. For instance, as a function of dead servers and incoming workload we could decide which servers to selectively turn on/off while still maintaining a desired level of performance. While evaluating each such choice is challenging, we demonstrate that arriving at the best and worst-case design is tractable. We further demonstrate that projected lifetimes of these extreme cases are very close to each other, often no more than 10% different. One way to interpret this number is, from a reliability perspective the utility of keeping machines as cold spares within the container, in anticipation of server failures, is not too different than starting out with all machines active. So as we engineer the containers in sophisticated ways for cost and performance, we can arrive at the associated reliability estimates using a simpler more-tractable approximation. We demonstrate that these bounds are robust to general distributions for failure times of servers. We hope that this paper stirs up a number of research investigations geared towards understanding these next generation data center building blocks. This involves both improving the models and corroborating them with field data.

/pdf/modular-data-centers-how-to-design-them-77yovlnvgc.pdf

Modular data centers: how to design them?

ModelNet is a network emulator designed for repeatable, large-scale experimentation with real networked systems. This talk introduces the ideas behind ModelNet that have made it a successful experimental platform. Beyond these core concepts, the talk highlights the latest additions to our methodology to test the next generation of network protocols and applications. Many of these developments address the datacenter compute environment: high-capacity networks, sophisticated infrastructure software (storage and virtualization), and complex network load. While these efforts significantly extend ModelNet's capabilities, there remain a number of open challenges, including incorporating new performance objectives (energy) and multicore architectures.

/pdf/modelnet-towards-a-datacenter-emulation-environment-452eujwzyz.pdf

ModelNet: Towards a datacenter emulation environment

One important question facing both network designers and distributed application developers is the interaction of the communication of a single network service or application with aggregate background traffic conditions. Unfortunately, network services are evaluated with typically no competing background traffic or, in the best case, ad hoc and simplistic traffic models. A related question is the effect that widely varying network traffic patterns have on network planning and resource allocation. For instance, the predicted growth of one application versus another (e.g., multimedia versus instant messaging) may have dramatically different impacts on a network’s traffic matrix. Yet, there is currently no way to quantify such effects. Thus, this paper proposes Swing, a flexible workload generator that accurately captures the packet interactions of a wide variety of applications based on a simple set of parameters. Our initial implementation includes settings for HTTP, P2P, and multimedia applications. We verify the accuracy of our application models by extracting application characteristics from available large-scale packet traces and by validating our generated traces against these same traces. We run Swing in ModelNet, a scalable and accurate network emulator to evaluate the interactions of distributed applications with a variety of traffic mixes. We show how to use these runs to measure dynamically changing router queue occupancy to “play back” realistic background traffic scenarios without actually generating any traffic. Finally, we use Swing to model the effect of traffic scenarios and topology on aggregate network load, for instance, as a network planning tool.

/pdf/swing-generating-realistic-background-packet-traces-for-3787jpbhgr.pdf

Kashi Venkatesh Vishwanath

Papers

Characterizing cloud computing hardware reliability

Modular data centers: how to design them?

ModelNet: Towards a datacenter emulation environment

Swing: Generating Realistic Background Packet Traces for Large-Scale Internet Topologies