Yashar Ganjali

Kandoo: a framework for efficient and scalable offloading of control applications

Limiting the overhead of frequent events on the control plane is essential for realizing a scalable Software-Defined Network. One way of limiting this overhead is to process frequent events in the data plane. This requires modifying switches and comes at the cost of visibility in the control plane. Taking an alternative route, we propose Kandoo, a framework for preserving scalability without changing switches. Kandoo has two layers of controllers: (i) the bottom layer is a group of controllers with no interconnection, and no knowledge of the network-wide state, and (ii) the top layer is a logically centralized controller that maintains the network-wide state. Controllers at the bottom layer run only local control applications (i.e., applications that can function using the state of a single switch) near datapaths. These controllers handle most of the frequent events and effectively shield the top layer. Kandoos design enables network operators to replicate local controllers on demand and relieve the load on the top layer, which is the only potential bottleneck in terms of scalability. Our evaluations show that a network controlled by Kandoo has an order of magnitude lower control channel consumption compared to normal OpenFlow networks.

Characterization of failures in an operational IP backbone network

As the Internet evolves into a ubiquitous communication infrastructure and supports increasingly important services, its dependability in the presence of various failures becomes critical. In this paper, we analyze IS-IS routing updates from the Sprint IP backbone network to characterize failures that affect IP connectivity. Failures are first classified based on patterns observed at the IP-layer; in some cases, it is possible to further infer their probable causes, such as maintenance activities, router-related and optical layer problems. Key temporal and spatial characteristics of each class are analyzed and, when appropriate, parameterized using well-known distributions. Our results indicate that 20% of all failures happen during a period of scheduled maintenance activities. Of the unplanned failures, almost 30% are shared by multiple links and are most likely due to router-related and optical equipment-related problems, respectively, while 70% affect a single link at a time. Our classification of failures reveals the nature and extent of failures in the Sprint IP backbone. Furthermore, our characterization of the different classes provides a probabilistic failure model, which can be used to generate realistic failure scenarios, as input to various network design and traffic engineering problems.

On scalability of software-defined networking

In this article, we deconstruct scalability concerns in software-defined networking and argue that they are not unique to SDN. We explore the often voiced concerns in different settings, discuss scalability trade-offs in the SDN design space, and present some recent research on SDN scalability. Moreover, we enumerate overlooked yet important opportunities and challenges in scalability beyond the commonly used performance metrics.

Load balancing in ad hoc networks: single-path routing vs. multi-path routing

Multi-path routing has been studied thoroughly in the context of wired networks. Ii has been shown that using multiple paths to route messages between any source-destination pair of nodes (instead of using a single path) balances the load more evenly throughout the network. The common belief is that the same is true for ad hoc networks, i.e., multi-path routing balances the load significantly better than single-path routing. We show that this is not necessarily the case. We introduce a new model for evaluating the load balance under multi-path routing, when the paths chosen are the first K shortest paths (for a pre-specified K). Using this model, we show that unless we use a very large number of paths (which is very costly and therefore infeasible) the load distribution is almost the same as single shortest path routing. This is in contrary to the previous existing results which assume that multi-path routing distributes the load uniformly.

Lockr: social access control for web 2.0

Sharing personal content online is surprisingly hard despite the recent emergence of a huge number of content sharing systems and sites. These systems suffer from several drawbacks: they each have a different way of providing access control which cannot be used with other systems; moving to a new system is a lengthy process and requires registration and invitation of all ones friends to the new system; and the rules for access control are complicated and become more so as our networks of online friends grow. In this paper, we present Lockr - an access control scheme based on social relationships that makes sharing personal content easy. Lockr separates social networking information from the content sharing mechanisms, thereby eliminating the need for users to maintain many site-specific copies of their social networks. We describe Lockrs design, security properties, and limitations. We also present how we integrated Lockr with two popular systems for sharing content online - BitTorrent and Flickr.

Experimental study of router buffer sizing

During the past four years, several papers have proposed rules for sizing buffers in Internet core routers. Appenzeller et al. suggest that a link needs a buffer of size O(C/√N), where C is the capacity of the link, and N is the number of flows sharing the link. If correct, buffers could be reduced by 99% in a typical backbone router today without loss in throughput. Enachecsu et al., and Raina et al. suggest that buffers can be reduced even further to 20-50 packets if we are willing to sacrifice a fraction of link capacities, and if there is a large ratio between the speed of core and access links. If correct, this is a five orders of magnitude reduction in buffer sizes. Each proposal is based on theoretical analysis and validated using simulations. Given the potential benefits (and the risk of getting it wrong!) it is worth asking if these results hold in real operational networks. In this paper, we report buffer-sizing experiments performed on real networks - either laboratory networks with commercial routers as well as customized switching and monitoring equipment (UW Madison, Sprint ATL, and University of Toronto), or operational backbone networks (Level 3 Communications backbone network, Internet2, and Stanford). The good news: Subject to the limited scenarios we can create, the buffer sizing results appear to hold. While we are confident that the O(C/√N) will hold quite generally for backbone routers, the 20-50 packet rule should be applied with extra caution to ensure that network components satisfy the underlying assumptions.

Buffer sizing in all-optical packet switches

Packet-switched routers need buffers during times of congestion. We show that a combined input-output queued router needs no more buffering than an output queued router. Using simulations, we show that 10-20 packet buffers are enough.

Optical packet buffers for backbone internet routers

If optical routers are to become reality, we will need several new optical technologies, one of which is to build sufficiently large optical buffers. Building optical buffers for routers is daunting: Todays electronic routers often hold millions of packets, which is well beyond the capabilities of optical technology. In this paper, we argue that two new results offer a solution. First, we show that the size of buffers in backbone routers can be made very small-just about 20 packets per linecard-at the expense of a small loss in throughput. Second, we show that integrated delay line optical buffers can store a few dozen packets on a photonic chip. With the combination of these two results, we conclude that future Internet routers could use optical buffers.

Rethinking end-to-end congestion control in software-defined networks

TCP is designed to operate in a wide range of networks. Without any knowledge of the underlying network and traffic characteristics, TCP is doomed to continuously increase and decrease its congestion window size to embrace changes in network or traffic. In light of emerging popularity of centrally controlled Software-Defined Networks (SDNs), one might wonder whether we can take advantage of the global network view available at the controller to make faster and more accurate congestion control decisions. In this paper, we identify the need and the underlying requirements for a congestion control adaptation mechanism. To this end, we propose OpenTCP as a TCP adaptation framework that works in SDNs. OpenTCP allows network operators to define rules for tuning TCP as a function of network and traffic conditions. We also present a preliminary implementation of OpenTCP in a ~4000 node data center.

Integrated Photonics for Low-Power Packet Networking

Communications interconnects and networks will continue to play a large role in contributing to the global carbon footprint, especially in data center and cloud-computing applications exponential growth in capacity. Key to maximizing the benefits of photonics technology is highly functional, lower power, and large-scale photonics integration. In this paper, we report on the latest advances in the photonic integration technologies used for asynchronous optical packet switching using an example photonic integrated switched optical router, the label switched optical router architecture. We report measurements of the power consumed by the photonic circuits in performing their intended function, the electronics required to bias the photonics, processing electronics, and required cooling technology. Data is presented to show that there is room (potentially greater than 10 ×) for improvement in the router packet-forwarding plane. The purpose of this exercise is not to provide a comparison of all-optical versus electronic routers, rather to present a data point on actual measurements of the power contributions for various photonic integration technologies of an all-optical packet router that has been demonstrated and conclude, where the technology can move to reduce power consumption for high-capacity packet routing systems.