We present a time-series analysis of Cogent's inter-continental network. The analysis is based on descriptions of Cogent's routers and their interfaces, collected each week for more than one year. These descriptions are collected from public reverse DNS records, which we cross-validate using iffinder, a full Internet scan, and limited ground truth data provided by Cogent. For example, our dataset, which we make available to the research community, shows that while the number of Cogent routers grew by approximately 11.3 each week, the average number of interfaces per router, and the effective diameter of the inferred network remained stable over the same period. Our collected dataset includes information about interface types, port identifications, router locations, peer and customer attachments, and more.

We present the design, implementation, and evaluation of an API for applications to control a software-defined network (SDN). Our API is implemented by an OpenFlow controller that delegates read and write authority from the network's administrators to end users, or applications and devices acting on their behalf. Users can then work with the network, rather than around it, to achieve better performance, security, or predictable behavior. Our API serves well as the next layer atop current SDN stacks. Our design addresses the two key challenges: how to safely decompose control and visibility of the network, and how to resolve conflicts between untrusted users and across requests, while maintaining baseline levels of fairness and security. Using a real OpenFlow testbed, we demonstrate our API's feasibility through microbenchmarks, and its usefulness by experiments with four real applications modified to take advantage of it.

Data processing frameworks such as MapReduce [8] and Dryad [11] are used today in business environments where customers expect guaranteed performance. To date, however, these systems are not capable of providing guarantees on job latency because scheduling policies are based on fair-sharing, and operators seek high cluster use through statistical multiplexing and over-subscription. With Jockey, we provide latency SLOs for data parallel jobs written in SCOPE. Jockey precomputes statistics using a simulator that captures the job's complex internal dependencies, accurately and efficiently predicting the remaining run time at different resource allocations and in different stages of the job. Our control policy monitors a job's performance, and dynamically adjusts resource allocation in the shared cluster in order to maximize the job's economic utility while minimizing its impact on the rest of the cluster. In our experiments in Microsoft's production Cosmos clusters, Jockey meets the specified job latency SLOs and responds to changes in cluster conditions.