SLICED PROGRAMMABLE NETWORKSOpenFlow [4] has been demonstrated as a way for researchers to run networking experiments in their production network. Last year, we demonstrated how an OpenFlow controller running on NOX [3] could move VMs seamlessly around an OpenFlow network [1]. While OpenFlow has potential [2] to open control of the network, only one researcher can innovate on the network at a time. What is required is a way to divide, or slice, network resources so that researchers and network administrators can use them in parallel. Network slicing implies that actions in one slice do not negatively affect other slices, even if they share the same underlying physical hardware. A common network slicing technique is VLANs. With VLANs, the administrator partitions the network by switch port and all traffic is mapped to a VLAN by input port or explicit tag. This coarse-grained type of network slicing complicates more interesting experiments such as IP mobility or wireless handover.Here, we demonstrate FlowVisor, a special purpose OpenFlow controller that allows multiple researchers to run experiments safely and independently on the same production OpenFlow network. To motivate FlowVisor's flexibility, we demonstrate four network slices running in parallel: one slice for the production network and three slices running experimental code (Figure 1). Our demonstration runs on real network hardware deployed on our production network 1 at Stanford and a wide-area test-bed with a mix of wired and wireless technologies.

In the past couple of years we've seen quite a change in the wireless industry: Handsets have become mobile computers running user-contributed applications on (potentially) open operating systems. It seems we are on a path towards a more open ecosystem; one that has been previously closed and proprietary. The biggest winners are the users, who will have more choice among competing, innovative ideas.The same cannot be said for the wireless network infrastructure, which remains closed and (mostly) proprietary, and where innovation is bogged down by a glacial standards process. Yet as users, we are surrounded by abundant wireless capacity and multiple wireless networks (WiFi and cellular), with most of the capacity off-limits to us. It seems industry has little incentive to change, preferring to hold onto control as long as possible, keeping an inefficient and closed system in place.This paper is a "call to arms" to the research community to help move the network forward on a path to greater openness. We envision a world in which users can move freely between any wireless infrastructure, while providing payment to infrastructure owners, encouraging continued investment. We think the best path to get there is to separate the network service from the underlying physical infrastructure, and allow rapid innovation of network services, contributed by researchers, network operators, equipment vendors and third party developers.We propose to build and deploy an open-but backward compatible-wireless network infrastructure that can be easily deployed on college campuses worldwide. Through virtualization, we allow researchers to experiment with new network services directly in their production network.

No abstract

Now that our smartphones have multiple interfaces (WiFi, 3G, 4G, etc.), we have preferences for which interfaces an application may use. We may prefer to stream video over WiFi because it is fast, but VoIP over 3G because it gives continued connectivity. We also have relative preferences, such as giving Netflix twice as much capacity as Dropbox. This means our mobile devices need to schedule packets in keeping with our preferences while making use of all the capacity available. This is the natural domain of fair queuing, and this paper is about the design of a packet scheduler to meet these requirements. We show that traditional fair queueing schedulers cannot take into account a user's preferences for some interfaces over others. We present a novel packet scheduler called miDRR that meets our needs by generalizing DRR for multiple interfaces. We demonstrate a prototype running in Linux and show that it works correctly and can easily run at the speeds we need.

There has usually been a clean separation between networks, and the applications that use them. Applications send packets over a simple socket API; the network delivers them. However, there are many occasions when applications can benefit from more direct interaction with the network, to observe more of the current network state, and have more control over its behavior. In this paper we explore some of the potential benefits of closer interaction between applications and the network. We exploit the emergence of so-called "software-defined networks" (SDN) built above network-wide control planes, and explore how to build a more "software friendly network". We present results from a preliminary exploration that provide network services to applications via an explicit communication channel.

No abstract

No abstract

Abstract-Determining how to transport delay-sensitive voice data has long been a problem in multimedia networking. The difficulty arises because voice and best-effort data are different by nature. It would not be fair to give priority to voice traffic and starve its best-effort counterpart; however, the voice data delivered might not be perceptible if each voice call is limited to the rate of an average TCP flow. To address the problem, we approach it from a user-centric perspective by tuning the voice data rate based on user satisfaction.Our contribution in this work is threefold. First, we investigate how Skype, the largest and fastest growing VoIP service on the Internet, adapts its voice data rate (i.e., the redundancy ratio) to network conditions. Second, by exploiting implementations of public domain codecs, we discover that Skype's mechanism is not really geared to user satisfaction. Third, based on a set of systematic experiments that quantify user satisfaction under different levels of packet loss and burstiness, we derive a concise model that allows user-centric redundancy control. The model can be easily incorporated into general VoIP services (not only Skype) to ensure consistent user satisfaction.