The recorded video of Marco’s presentation of DiCE at USENIX ATC’11 finally surfaced on the Web.

Effective resource management of virtualized environments that form the cloud computing backbone is a challenging task. State-of-the-art managements systems either rely on analytical models or testing different resource allocations by running actual experiments. Both approaches face a significant overhead once the workload changes. We introduce DejaVu – a framework that accelerates resource allocation in virtualized environments.  DejaVu achieves more than a factor of 10 speedup in adaptation time for each workload change relative to the state-of-the-art. By enabling quick adaptation, DejaVu saves up to 60% of the service provisioning cost. Dejan will present our work at ASPLOS in London in March 2012.

Power consumption of today’s datacenters is already significant and threatens to shortly hit the power wall – it is getting progressively harder to supply datacenter equipment with sufficient energy for power and cooling. We tackle this problem by proposing REsPoNse, a framework that effectively tries to achieve the energy-proportionality in both Internet and datacenter networks. The insight in REsPoNse is to identify a few energy-critical paths off-line, install them into network elements, and use a simple online element to redirect the traffic in a way that enables large parts of the network to enter a low-power state. Nedeljko presented this work at CoNEXT in December 2011.

Our paper A NICE Way to Test OpenFlow Applications has been accepted at NSDI 2012 (joint work with Jennifer Rexford from Princeton University).

The emergence of OpenFlow-capable switches enables exciting new network functionality, at the risk of programming errors that make communication less reliable. The centralized programming model, where a single controller program manages the network, seems to reduce the likelihood of bugs. However, the system is inherently distributed and asynchronous, with events happening at different switches and end hosts, and inevitable delays affecting communication with the controller. In this paper, we present efficient, systematic techniques for testing unmodified controller programs. Our NICE tool applies model checking to explore the state space of the entire system—the controller, the switches, and the hosts. Scalability is the main challenge, given the diversity of data packets, the large system state, and the many possible event orderings. To address this, we propose a novel way to augment model checking with symbolic execution of event handlers (to identify representative packets that exercise code paths on the controller). We also present a simplified OpenFlow switch model (to reduce the state space), and effective strategies for generating event interleavings likely to uncover bugs. Our prototype tests Python applications on the popular NOX platform. In testing three real applications—a MAC-learning switch, in-network server load balancing, and energy-efficient traffic engineering—we uncover eleven bugs.

Marco presented our DiCE demo at SIGCOMM 2011. The text of the submission is available here. Below is a screenshot of a prefix hijack (origin misconfiguration) attempt that our DiCE prototype detects on an Internet-like topology.

Powering the Internet consumes vast amounts of energy, and the discrepancy in trends between the ever-increasing Internet traffic and the slower increase of hardware energy efficiency threatens the Internet’s growth. We completed a project in which, in collaboration with Telefonica Research, we take an in-depth look at the problem of greening access networks (predominant factor in wired network energy consumption), identify three root problems, and propose practical solutions for their user- and ISP-parts. Overall, our results show that it is possible to save 66% of access network energy. If applied worldwide, this translates to saving 33 TWh per year (annual output of three nuclear power plants). Marco presented the work at SIGCOMM 2011 in Toronto (video).