Cloud computing infrastructures are increasingly being used by network-intensive applications that transfer significant amounts of data between the nodes on which they run. This paper shows that tenants can do a better job placing applications by understanding the underlying cloud network as well as the demands of the applications. To do so, tenants must be able to quickly and accurately measure the cloud network and profile their applications, and then use a network-aware placement method to place applications. This paper describes Choreo, a system that solves these problems. Our experiments measure Amazon's EC2 and Rackspace networks and use three weeks of network data from applications running on the HP Cloud network. We find that Choreo reduces application completion time by an average of 8%-14% (max improvement: 61%) when applications are placed all at once, and 22%-43% (max improvement: 79%) when they arrive in real-time, compared to alternative placement schemes.

Despite many years of work in wireless mesh networks built using 802.11 radios, the performance and behavior of these networks in the wild is not well-understood. This lack of understanding is due in part to the lack of access to data from a wide range of these networks; most researchers have access to only one or two testbeds at any time. In recent years, however, 802.11 mesh networks networks have been deployed commercially and have real users who use the networks in a wide range of conditions. This paper analyzes data collected from 1407 access points in 110 different commercially deployed Meraki wireless mesh networks, constituting perhaps the largest study of real-world 802.11 networks to date. After analyzing a 24-hour snapshot of data collected from these networks, we answer questions from a variety of active research topics, such as the accuracy of SNR-based bit rate adaptation, the impact of opportunistic routing, and the prevalence of hidden terminals. The size and diversity of our data set allows us to analyze claims previously only made in small-scale studies. In particular, we find that the SNR of a link is a good indicator of the optimal bit rate for that link, but that one could not make an SNR-to-bit rate look-up table that was accurate for an entire network. We also find that an ideal opportunistic routing protocol provides little to no benefit on most paths, and that "hidden triples"---network topologies that can lead to hidden terminals--are more common than suggested in previous work, and increase in proportion as the bit rate increases.

Traffic delays and congestion are a major source of inefficiency, wasted fuel, and commuter frustration. Measuring and localizing these delays, and routing users around them, is an important step towards reducing the time people spend stuck in traffic. As others have noted, the proliferation of commodity smartphones that can provide location estimates using a variety of sensors---GPS, WiFi, and/or cellular triangulation---opens up the attractive possibility of using position samples from drivers' phones to monitor traffic delays at a fine spatiotemporal granularity. This paper presents VTrack, a system for travel time estimation using this sensor data that addresses two key challenges: energy consumption and sensor unreliability. While GPS provides highly accurate location estimates, it has several limitations: some phones don't have GPS at all, the GPS sensor doesn't work in "urban canyons" (tall buildings and tunnels) or when the phone is inside a pocket, and the GPS on many phones is power-hungry and drains the battery quickly. In these cases, VTrack can use alternative, less energy-hungry but noisier sensors like WiFi to estimate both a user's trajectory and travel time along the route. VTrack uses a hidden Markov model (HMM)-based map matching scheme and travel time estimation method that interpolates sparse data to identify the most probable road segments driven by the user and to attribute travel times to those segments. We present experimental results from real drive data and WiFi access point sightings gathered from a deployment on several cars. We show that VTrack can tolerate significant noise and outages in these location estimates, and still successfully identify delay-prone segments, and provide accurate enough delays for delay-aware routing algorithms. We also study the best sampling strategies for WiFi and GPS sensors for different energy cost regimes.

Incentives play a crucial role in BitTorrent, motivating users to upload to others to achieve fast download times for all peers. Though long believed to be robust to strategic manipulation, recent work has empirically shown that BitTorrent does not provide its users incentive to follow the protocol. We propose an auction-based model to study and improve upon BitTorrent's incentives. The insight behind our model is that BitTorrent uses, not tit-for-tat as widely believed, but an auction to decide which peers to serve. Our model not only captures known, performance-improving strategies, it shapes our thinking toward new, effective strategies. For example, our analysis demonstrates, counter-intuitively, that BitTorrent peers have incentive to intelligently under-report what pieces of the file they have to their neighbors. We implement and evaluate a modification to BitTorrent in which peers reward one another with proportional shares of bandwidth. Within our game-theoretic model, we prove that a proportional-share client is strategy-proof. With experiments on PlanetLab, a local cluster, and live downloads, we show that a proportional-share unchoker yields faster downloads against BitTorrent and BitTyrant clients, and that under-reporting pieces yields prolonged neighbor interest.