AT&T Labs Research — Leading Invention, Driving Innovation

The definitive version was published in 2012. , 2012-10-22, http://www.cnsm-conf.org/2012/index.html

{Data center networks have started to play increasingly important roles in today's Internet. Popular web-based services and critical enterprise applications are hosted in large data centers. More recent advances like cloud computing and cellular-based data usage have only increased the importance of data centers. With the increasing importance, however, also comes increasing complexity. Supporting the wide-array of applications and traffic types while meeting all their performance and security requirements results in complex network designs. The result of this complexity is that managing these networks has never been more difficult. In this paper, we focus on providing one of the key building blocks of network management: the ability to determine how traffic flows in the network. This information is fundamental to many different network management tasks including troubleshooting, capacity planning, and what-if analysis. Towards that end, we present Chartis, a system which performs per-packet path inference in a data center. Chartis takes as input device configurations and the network's physical topology and outputs the path of a packet in the network. Specifically, Chartis performs per-hop path inference based on a simplified model of layer-3 routing, layer-2 switching, and the most commonly used routing and forwarding mechanisms. To show Chartis diverse applicability, we perform path inference within a campus network and on multiple data centers serving the 3G network of a major cellular service provider. Using routing information collected from these networks, we validate the correctness of the inferred paths. Our results show that Chartis can quickly and accurately determine paths traversed by packets even in complex data center networks, making it a valuable addition to a network operator's toolbox.}

The definitive version was published in proceedings of OFC 2011 (Optical Society of America). , 2011-03-06

{We describe RFC, a new capability that minimizes customer outages during software and hardware upgrades in ISP networks. RFC is being used by a large Tier-1 ISP to upgrade access routers supporting thousands of customers.}

(c) ACM, 2011. This is the author's version of the work. It is posted here by permission of ACM for your personal use. Not for redistribution. The definitive version was published in ACM SIGCOMM Workshop on Hot Topics in Networks , 2011-10-15.

{Cloud service providers use replication across geographically distributed data centers to improve end-to-end performance as well as to offer high reliability under failures. Content replication often involves the transfer of huge data sets over the wide area network and demands high backbone transport capacity. In this paper, we discuss how a Globally Reconfigurable Intelligent Photonic Network (GRIPhoN) between data centers could improve operational flexibility for cloud service providers. The proposed GRIPhoN architecture is an extension of earlier work [34] and can provide a bandwidth-on-demand service ranging from low data rates (e.g., 1 Gbps) to high data rates (e.g., 10-40 Gbps). The inter-data center communication network which is currently statically provisioned could be dynamically configured based on demand. Today's backbone optical networks can take several weeks to provision a customer's private line connection. GRIPhoN would enable cloud operators to dynamically set up and tear down their connections (sub-wavelength or wavelength rates) within a few minutes. GRIPhoN also offers cost-effective restoration capabilities at wavelength rates and automated bridge-and-roll of private line connections to minimize the impact of planned maintenance activities.}